INDEX

Explanations

geographical features and place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 vill

-0.15

ighth

-0.14

retch

-0.14

MSG

-0.14

-0.13

raf

-0.13

Î¿Îº

-0.13

rove

-0.13

":[{↵

-0.13

ietf

-0.13

POSITIVE LOGITS

 Creek

0.21

Gul

0.17

Run

0.17

 Field

0.17

 Point

0.16

 Pass

0.15

 Complex

0.15

nze

0.15

 Shortcut

0.15

Gap

0.15

Activations Density 0.122%

geographical features and place names

No Comments

No Known Activations