INDEX

Explanations

words and phrases indicating quantity or frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

rana

-0.19

åº«

-0.16

cit

-0.15

æºĲ

-0.14

 Vernon

-0.14

unnable

-0.14

VISIBLE

-0.14

 Liberty

-0.14

ierarchy

-0.13

POSITIVE LOGITS

 laps

0.15

olutely

0.14

 disp

0.14

ë§Ĳ

0.14

íĴĪ

0.13

 Ø£Ø´

0.13

pon

0.13

 premature

0.13

ipers

0.13

Activations Density 0.076%

words and phrases indicating quantity or frequency

No Comments

No Known Activations