INDEX

Explanations

expressions of doubt or skepticism about situations or outcomes

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

 Leer

-0.15

Ø§Ø®Øª

-0.15

acula

-0.15

RootElement

-0.15

oom

-0.14

æĤŁ

-0.14

jing

-0.14

 Parad

-0.14

lyn

-0.14

jie

-0.14

POSITIVE LOGITS

 unlikely

0.63

unlikely

0.57

 doubt

0.53

 doubtful

0.53

 Doub

0.47

 doubts

0.45

 doubted

0.42

 likelihood

0.41

 probability

0.39

 odds

0.39

Activations Density 0.275%

expressions of doubt or skepticism about situations or outcomes

No Comments

No Known Activations

expressions of doubt or skepticism about situations or outcomes

No Comments

No Known Activations