INDEX

Explanations

references to domestic issues and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

enberg

-0.19

flen

-0.15

ecies

-0.14

èº«

-0.14

jiÅ¡Å¥

-0.14

ÑĨÑĮ

-0.14

iversite

-0.14

ÐµÑı

-0.14

ven

-0.13

oon

-0.13

POSITIVE LOGITS

 violence

0.16

ized

0.16

ization

0.15

itat

0.15

ity

0.15

idade

0.14

idad

0.14

Ð¸ÑĢÐ¾Ð²

0.14

ovice

0.14

ated

0.14

Activations Density 0.009%

references to domestic issues and contexts

No Comments

No Known Activations