INDEX

Explanations

words indicating necessity or requirement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 grown

-0.15

 ëĭ´

-0.14

sonian

-0.14

iju

-0.14

Ã¢m

-0.14

ipa

-0.14

NONE

-0.14

aleb

-0.14

ohon

-0.14

oho

-0.13

POSITIVE LOGITS

 source

0.27

 sources

0.25

source

0.22

 Sources

0.21

sources

0.20

SOURCE

0.20

 either

0.20

 Source

0.20

 SOURCE

0.19

æºĲ

0.19

Activations Density 0.008%

words indicating necessity or requirement

No Comments

No Known Activations