INDEX

Explanations

phrases that express future intentions or hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

uje

-0.17

 underwent

-0.14

FFE

-0.13

ãģĭãĤīãģ¯

-0.13

ynamodb

-0.13

 Ð¸ÑģÐ¿Ð¾Ð»ÑĮÐ·ÑĥÑİÑĤ

-0.13

 undergo

-0.12

ADS

-0.12

ined

-0.12

asl

-0.12

POSITIVE LOGITS

 being

0.60

be

0.60

 Ð±ÑĭÑĤÑĮ

0.55

being

0.54

 bÃ½t

0.52

 essere

0.49

 Being

0.49

 Ð±ÑĥÑĤÐ¸

0.46

 Ãªtre

0.45

 byÄĩ

0.45

Activations Density 0.368%

phrases that express future intentions or hypothetical scenarios

No Comments

No Known Activations

phrases that express future intentions or hypothetical scenarios

No Comments

No Known Activations