INDEX

Explanations

references to gender inequality and discrimination in political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

aler

-0.15

abin

-0.15

.Companion

-0.15

inalg

-0.14

via

-0.14

aggio

-0.14

 ExecutionContext

-0.14

inish

-0.13

owler

-0.13

oller

-0.13

POSITIVE LOGITS

Flip

0.17

 flip

0.17

flip

0.16

 Flip

0.16

lys

0.14

gross

0.14

íİ¸

0.14

 daher

0.14

imp

0.13

Activations Density 0.660%

references to gender inequality and discrimination in political contexts

No Comments

No Known Activations