INDEX

Explanations

words related to social or political issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

bon

-0.15

ÑĢÑİ

-0.14

RELEASE

-0.14

 Hubbard

-0.14

Ì§

-0.14

 bombed

-0.14

ara

-0.14

alchemy

-0.14

POSITIVE LOGITS

ibur

0.16

Cz

0.14

ãģ¡ãĤĩ

0.14

æĹıèĩªæ²»

0.14

 trait

0.14

 Constitutional

0.14

 handjob

0.14

asel

0.13

 Enum

0.13

 national

0.13

Activations Density 0.000%

words related to social or political issues

No Comments

No Known Activations