INDEX

Explanations

terms related to discrimination and bias

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ioned

-0.21

cn

-0.16

ittings

-0.15

loy

-0.15

pij

-0.14

anh

-0.14

orman

-0.14

jar

-0.14

ends

-0.14

oral

-0.14

POSITIVE LOGITS

Against

0.22

 against

0.22

 based

0.21

 Against

0.20

against

0.20

 Based

0.18

Based

0.16

 Discrim

0.16

inating

0.15

Activations Density 0.017%

terms related to discrimination and bias

No Comments

No Known Activations