INDEX

Explanations

instances of the word "from" as well as references to analysis and data sources

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

unde

-0.18

ULA

-0.16

uder

-0.15

à¸¥à¸²

-0.15

yst

-0.15

Î½Ïī

-0.15

ula

-0.14

vala

-0.14

 Maur

-0.14

jur

-0.14

POSITIVE LOGITS

oft

0.16

 Block

0.15

åį

0.15

ì¦ĺ

0.15

oint

0.15

Sab

0.14

 block

0.14

bane

0.14

ointment

0.14

 ÑģÐ½Ð°

0.14

Activations Density 0.046%

instances of the word "from" as well as references to analysis and data sources

No Comments

No Known Activations