INDEX

Explanations

phrases indicating professional expertise and experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Bolt

-0.14

iler

-0.14

Å¼y

-0.14

ennes

-0.13

 å¢

-0.13

 Actions

-0.13

enan

-0.13

geist

-0.13

.GetCurrent

-0.13

POSITIVE LOGITS

 experience

0.87

experience

0.71

 Experience

0.71

Experience

0.65

 experiencia

0.56

 experiences

0.56

_experience

0.54

ç»ıéªĮ

0.53

 expÃ©rience

0.51

perience

0.45

Activations Density 0.359%

phrases indicating professional expertise and experience

No Comments

No Known Activations