INDEX

Explanations

references to computers and computing technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ott

-0.16

ager

-0.15

udge

-0.15

inois

-0.15

rist

-0.15

elage

-0.14

bler

-0.14

ener

-0.14

ory

-0.14

OK

-0.13

POSITIVE LOGITS

ized

0.31

ization

0.24

ised

0.23

IZED

0.21

isation

0.21

íĵ¨íĦ°

0.19

/table

0.18

IZATION

0.17

-readable

0.17

ize

0.17

Activations Density 0.017%

references to computers and computing technology

No Comments

No Known Activations