INDEX

Explanations

instances of surprise and unexpectedness 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 @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

à¤®à¤°

-0.16

mind

-0.16

mes

-0.16

gie

-0.15

enz

-0.14

une

-0.14

mie

-0.14

 Centers

-0.14

çĽĽ

-0.14

CRY

-0.14

POSITIVE LOGITS

ingly

0.36

kus

0.17

pon

0.17

ively

0.16

yers

0.16

ably

0.16

orks

0.15

/conf

0.15

 factor

0.15

Activations Density 0.028%

instances of surprise and unexpectedness in various contexts

No Known Activations