INDEX

Explanations

references to the color "white."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

acles

-0.16

nt

-0.16

nown

-0.16

enne

-0.16

rian

-0.15

istic

-0.15

ogle

-0.15

acle

-0.15

nts

-0.14

ret

-0.14

POSITIVE LOGITS

-collar

0.20

 supremacist

0.18

ened

0.17

-white

0.17

papers

0.16

paper

0.15

isz

0.15

/black

0.15

enment

0.15

0.14

Activations Density 0.041%

references to the color "white."

No Comments

No Known Activations