INDEX

Explanations

references to political accountability and hypocrisy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

onta

-0.16

Ð»ÑĥÐ±

-0.15

ssue

-0.14

lub

-0.14

'])){

-0.13

ÑĪÑĮ

-0.13

ãĥĢãĥ¼

-0.13

eldorf

-0.13

essa

-0.13

andal

-0.13

POSITIVE LOGITS

 supposed

0.44

 supposedly

0.35

 suppose

0.28

 purported

0.27

 alleged

0.23

 claimed

0.23

 allegedly

0.22

 should

0.21

pur

0.21

 meant

0.19

Activations Density 0.281%

references to political accountability and hypocrisy

No Comments

No Known Activations