INDEX

Explanations

phrases associated with shock or surprise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

-ci

-0.16

fty

-0.15

 Burnett

-0.14

ollapsed

-0.14

rowse

-0.14

amental

-0.14

Ð±Ñĥ

-0.14

IAL

-0.14

Lei

-0.14

POSITIVE LOGITS

ingly

0.25

ively

0.19

aper

0.16

rchive

0.15

sp

0.15

mong

0.15

ORTH

0.15

rp

0.15

ysqli

0.14

¨

0.14

Activations Density 0.017%

phrases associated with shock or surprise

No Comments

No Known Activations