INDEX

Explanations

contradictory or negating statements in a text

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

MES

-0.16

sto

-0.15

in

-0.14

kker

-0.14

beck

-0.14

à¤¹à¤°

-0.14

uyáº¿t

-0.14

rij

-0.14

kp

-0.14

Î»Î¿Î½

-0.14

POSITIVE LOGITS

 true

0.56

true

0.44

 True

0.41

 TRUE

0.39

True

0.36

 case

0.35

TRUE

0.34

(true

0.32

 verdade

0.31

	true

0.31

Activations Density 0.128%

contradictory or negating statements in a text

No Comments

No Known Activations