INDEX

Explanations

references to political candidates and elections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-Based

-0.18

-based

-0.17

ÑĤÐ°Ð¶

-0.14

-made

-0.14

askets

-0.14

tÄ±ÄŁ

-0.14

brids

-0.13

Ä©

-0.13

ires

-0.13

POSITIVE LOGITS

 candidate

0.34

 candidates

0.33

åĢĻ

0.32

 Candidate

0.29

candidate

0.29

 hopeful

0.28

 íĽĦë³´

0.28

 prospects

0.27

_candidate

0.27

 Candidates

0.27

Activations Density 0.243%

references to political candidates and elections

No Comments

No Known Activations