INDEX

Explanations

connections to authoritative figures and organizational roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 ActiveForm

-0.14

âĢ¦↵

-0.13

/GPL

-0.13

uien

-0.13

GMEM

-0.13

...)↵

-0.13

âĢ¦↵↵

-0.12

âĢ¦"

-0.12

,âĢ¦

-0.12

ylland

-0.12

POSITIVE LOGITS

è§

0.13

atur

0.13

zet

0.12

 bruk

0.12

 nackte

0.11

ilo

0.11

_portal

0.11

ik

0.11

://

0.10

 rank

0.10

Activations Density 1.425%

connections to authoritative figures and organizational roles

No Comments

No Known Activations