INDEX

Explanations

mentions of the word "White" in various contexts

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

nd

-0.20

nt

-0.17

 purple

-0.16

rian

-0.16

epad

-0.15

ments

-0.15

istic

-0.15

nya

-0.14

roz

-0.14

scope

-0.14

POSITIVE LOGITS

 supremacist

0.21

-collar

0.21

-white

0.20

bread

0.20

aker

0.20

WHITE

0.19

-trash

0.19

White

0.19

paper

0.19

papers

0.19

Activations Density 0.043%

mentions of the word "White" in various contexts

No Comments

No Known Activations