INDEX

Explanations

various forms of punctuation and questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

redits

-0.15

avad

-0.15

utton

-0.15

igate

-0.14

Uploaded

-0.14

_BUSY

-0.14

ãĤ¤ãĥĪ

-0.14

oso

-0.13

azo

-0.13

istration

-0.13

POSITIVE LOGITS

Hi

0.22

hi

0.19

Hi

0.19

ossal

0.18

HI

0.18

ELLOW

0.18

 Hello

0.18

 hello

0.17

hello

0.16

_bulk

0.16

Activations Density 0.088%

various forms of punctuation and questions

No Comments

No Known Activations