INDEX

Explanations

mentions of the word "Yale" and related institutions or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

stands

-0.17

 çĬ

-0.17

seau

-0.16

trand

-0.15

ARY

-0.14

eldom

-0.14

oulouse

-0.14

 tiener

-0.14

iek

-0.14

æłª

-0.14

POSITIVE LOGITS

cade

0.16

osy

0.15

$MESS

0.15

jem

0.14

lew

0.14

ameda

0.14

ooth

0.14

ÂŃi

0.14

ront

0.14

Ã¼ne

0.14

Activations Density 0.015%

mentions of the word "Yale" and related institutions or context

No Comments

No Known Activations