INDEX

Explanations

references to political positions and significant appointments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

æľĢè¿ĳ

-0.16

Ð¾ÑģÐ¾Ð±

-0.16

 jusqu

-0.16

åĮħæĭ¬

-0.15

Until

-0.15

ulos

-0.15

æĪĸèĢħ

-0.15

 æĺ¯åĲ¦

-0.15

 jika

-0.14

 æīĢ

-0.14

POSITIVE LOGITS

 after

0.35

 exactly

0.30

 following

0.30

 less

0.30

 followed

0.28

 having

0.28

after

0.28

 foll

0.26

 just

0.26

 hours

0.26

Activations Density 0.712%

references to political positions and significant appointments

No Comments

No Known Activations