INDEX

Explanations

numerical values and identifiers related to statistics or records

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

stab

-0.16

 McCabe

-0.16

cba

-0.16

rada

-0.16

stre

-0.15

 METH

-0.14

/mat

-0.14

ffc

-0.14

ang

-0.13

atrice

-0.13

POSITIVE LOGITS

bul

0.17

0.16

erton

0.16

isp

0.15

imap

0.15

ermo

0.15

EntryPoint

0.14

Ð¸ÑĪ

0.14

RF

0.14

ived

0.14

Activations Density 0.034%

numerical values and identifiers related to statistics or records

No Comments

No Known Activations