INDEX

Explanations

jewelry-related terminology and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ienne

-0.15

Ã£o

-0.14

iaux

-0.14

MainFrame

-0.14

Ø±Ø§Ùĩ

-0.14

stateParams

-0.14

enville

-0.14

isten

-0.14

 Bren

-0.14

POSITIVE LOGITS

pend

0.17

qq

0.16

ectl

0.15

omba

0.15

acro

0.14

icine

0.14

 Reed

0.14

hma

0.14

 pend

0.14

ancia

0.13

Activations Density 0.136%

jewelry-related terminology and descriptions

No Comments

No Known Activations