INDEX

Explanations

references to specific individuals and notable actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

aux

-0.17

icens

-0.15

ivy

-0.15

á»Ľp

-0.15

inaire

-0.15

plode

-0.14

vik

-0.14

rollo

-0.14

 Forget

-0.13

riger

-0.13

POSITIVE LOGITS

abeth

0.15

 Baldwin

0.15

Pred

0.15

mond

0.15

 Pred

0.15

âĻĢ

0.14

akis

0.14

 ÐŁÑĢÐµÐ´

0.14

 pred

0.14

uss

0.14

Activations Density 0.003%

references to specific individuals and notable actions

No Comments

No Known Activations