INDEX

Explanations

references to racism and related social issues

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

mers

-0.19

iers

-0.19

erte

-0.16

liers

-0.15

ANGE

-0.15

usch

-0.15

oby

-0.15

ah

-0.15

ogs

-0.15

Ð¼Ñĭ

-0.14

POSITIVE LOGITS

 tokenize

0.17

pta

0.16

IFA

0.15

.WinForms

0.15

alu

0.15

folio

0.14

allo

0.14

eum

0.14

PELL

0.14

Vectorizer

0.14

Activations Density 0.009%

references to racism and related social issues

No Comments

No Known Activations