INDEX

Explanations

certainty and assurance in statements

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

æŁĦ

-0.16

igest

-0.15

åĬ¹

-0.15

ullen

-0.14

ichte

-0.14

ÏģÏį

-0.14

pis

-0.14

Ø§ÙĦØ§

-0.13

als

-0.13

POSITIVE LOGITS

 sure

0.56

 certainty

0.54

sure

0.46

 Sure

0.46

Sure

0.39

 certain

0.39

 confidence

0.38

 cert

0.36

 confident

0.35

SURE

0.35

Activations Density 0.154%

certainty and assurance in statements

No Comments

No Known Activations