INDEX

Explanations

phrases indicating support or assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

resume

-0.15

asma

-0.15

xBB

-0.14

issy

-0.14

.ua

-0.14

-Za

-0.14

ìĸ´ëĤĺ

-0.14

away

-0.14

stamp

-0.14

 Mills

-0.13

POSITIVE LOGITS

_TestCase

0.17

 ready

0.16

bable

0.16

Ske

0.15

ardu

0.15

@Web

0.15

to

0.14

Skeleton

0.14

encion

0.14

plete

0.14

Activations Density 0.026%

phrases indicating support or assistance

No Comments

No Known Activations