INDEX

Explanations

names of authors and their affiliations in academic contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

á»īnh

-0.17

ongyang

-0.15

 Nuevo

-0.14

arpa

-0.14

loquent

-0.14

Ã¨o

-0.14

exampleInputEmail

-0.14

ppv

-0.13

>NN

-0.13

(CC

-0.13

POSITIVE LOGITS

ude

0.17

flater

0.15

ï¼

0.15

estr

0.14

ÑĢÐ¾Ð·

0.13

ellen

0.13

esthetic

0.13

auge

0.13

communic

0.13

Activations Density 0.135%

names of authors and their affiliations in academic contexts

No Comments

No Known Activations