INDEX

Explanations

phrases that describe objects held in hands or situations involving hands

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

din

-0.17

rib

-0.16

dorf

-0.15

Ø§ÙĬØ±

-0.15

emale

-0.14

 variant

-0.14

 round

-0.14

eki

-0.14

 with

-0.14

umb

-0.14

POSITIVE LOGITS

orde

0.16

 Ø¢Ùħ

0.15

trl

0.14

Ø§Ùĩ

0.14

 è©ķä¾¡

0.14

'gc

0.14

odiac

0.14

Virgin

0.13

ableView

0.13

abe

0.13

Activations Density 0.243%

phrases that describe objects held in hands or situations involving hands

No Comments

No Known Activations