INDEX

Explanations

names of companies and organizations or references to significant individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

cko

-0.18

ngo

-0.15

 taps

-0.15

Ú©ÛĮÙĦ

-0.15

REP

-0.15

]={↵

-0.15

imits

-0.14

ched

-0.14

_CID

-0.14

rvÃ©

-0.14

POSITIVE LOGITS

pent

0.14

aghan

0.14

Ã¥r

0.14

Trace

0.14

à¸¯

0.13

 Trace

0.13

oze

0.13

lor

0.13

ars

0.13

icos

0.13

Activations Density 0.098%

names of companies and organizations or references to significant individuals

No Comments

No Known Activations