INDEX

Explanations

numerical dates and times

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

hum

-0.17

ìĨį

-0.16

ndata

-0.15

hs

-0.15

igin

-0.14

hum

-0.14

 Moore

-0.14

Dj

-0.14

 process

-0.14

ada

-0.14

POSITIVE LOGITS

_define

0.16

toi

0.15

ÏįÎ½

0.14

ÃŃsto

0.14

eph

0.14

imate

0.14

rud

0.13

ÐµÐ½Ð·

0.13

ico

0.13

Ã¼zel

0.13

Activations Density 0.117%

numerical dates and times

No Comments

No Known Activations