INDEX

Explanations

verbs and phrases related to functionality and effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

arez

-0.15

ventus

-0.15

assen

-0.15

ÙħÙĤ

-0.15

duit

-0.14

UNS

-0.14

lou

-0.14

aurant

-0.13

uce

-0.13

AFP

-0.13

POSITIVE LOGITS

0.18

 magic

0.16

adlo

0.16

ios

0.16

asper

0.15

magic

0.15

eer

0.15

ivities

0.15

 well

0.15

 differently

0.15

Activations Density 0.059%

verbs and phrases related to functionality and effectiveness

No Comments

No Known Activations