INDEX

Explanations

references to the concept of "filling" or "filling roles" 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

eph

-0.17

Ð¾Ð¿Ð¾Ð»

-0.17

esti

-0.15

annis

-0.14

esis

-0.14

ely

-0.14

nte

-0.14

ement

-0.14

 Carr

-0.14

emode

-0.14

POSITIVE LOGITS

prung

0.15

itre

0.14

brook

0.14

ollipop

0.14

retch

0.14

filled

0.14

ipt

0.14

fill

0.14

stitial

0.14

chs

0.14

Activations Density 0.023%

references to the concept of "filling" or "filling roles" in various contexts

No Comments

No Known Activations