INDEX

Explanations

references to expert opinions and roles 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 ApplicationException

-0.14

ä¼´

-0.14

lescope

-0.14

 sponsors

-0.14

sponsor

-0.13

arious

-0.13

agn

-0.13

esa

-0.13

POSITIVE LOGITS

 experts

0.74

 expert

0.72

 Experts

0.65

expert

0.62

 Expert

0.60

Expert

0.56

 expertise

0.55

Experts

0.55

 specialists

0.45

 specialist

0.42

Activations Density 0.205%

references to expert opinions and roles in various contexts

No Comments

No Known Activations