INDEX

Explanations

expressions of confidence and self-assurance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ward

-0.18

ependency

-0.17

WARD

-0.15

aul

-0.15

alam

-0.15

 WaitForSeconds

-0.15

::<

-0.14

beiter

-0.14

umin

-0.14

à¥Ģà¤¤

-0.14

POSITIVE LOGITS

/conf

0.17

 confidence

0.17

/power

0.16

Ã©c

0.15

 Confidence

0.15

ably

0.15

vale

0.14

ghan

0.14

plx

0.14

 confident

0.14

Activations Density 0.024%

expressions of confidence and self-assurance

No Comments

No Known Activations