INDEX

Explanations

keywords related to activities and structures in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

antar

-0.17

amer

-0.16

IOC

-0.15

ìĿ´íĦ°

-0.14

.hardware

-0.14

 Ment

-0.14

 Chew

-0.14

dsl

-0.13

esel

-0.13

iver

-0.13

POSITIVE LOGITS

ulmasÄ±

0.15

laden

0.15

kor

0.15

ows

0.15

-type

0.14

coni

0.14

tokenId

0.14

iman

0.14

 Bren

0.14

 coal

0.13

Activations Density 0.031%

keywords related to activities and structures in various contexts

No Comments

No Known Activations