INDEX

Explanations

references to the concept of words and their significance

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

ogue

-0.15

greso

-0.15

erty

-0.14

ekl

-0.14

ave

-0.14

uÅ¡

-0.14

 funnel

-0.13

 Maul

-0.13

eway

-0.13

anv

-0.13

POSITIVE LOGITS

heimer

0.19

Ä±t

0.15

Î½Î¿Ïį

0.15

cen

0.14

éĶĭ

0.14

ofilm

0.14

 ëĵ¯

0.14

uably

0.14

 Words

0.14

ipo

0.14

Activations Density 0.031%

references to the concept of words and their significance

No Comments

No Known Activations