INDEX

Explanations

terms related to skating

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.19

egr

-0.16

 xOffset

-0.16

Ð¼ÐµÐ½Ð°

-0.16

brahim

-0.15

aceutical

-0.15

adera

-0.15

eÅŁ

-0.15

onder

-0.15

iyan

-0.15

POSITIVE LOGITS

sk

0.25

unk

0.23

imming

0.21

inned

0.21

UNK

0.20

unks

0.20

ateway

0.19

irting

0.19

-sk

0.19

ipp

0.19

Activations Density 0.009%

terms related to skating

No Comments

No Known Activations