INDEX

Explanations

references to terms or concepts that are coined or defined in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

omm

-0.16

iddles

-0.14

iga

-0.14

ÑĥÑģÐ°

-0.14

VICE

-0.14

oucher

-0.14

arah

-0.14

sez

-0.14

 komm

-0.13

Î¹Ïĥ

-0.13

POSITIVE LOGITS

ture

0.15

ddb

0.14

 scoff

0.14

/Gate

0.14

criptor

0.14

ÐµÐ¼Ð¾

0.14

ae

0.14

achat

0.13

itt

0.13

Activations Density 0.229%

references to terms or concepts that are coined or defined in various contexts

No Comments

No Known Activations