INDEX

Explanations

phrases and expressions of confusion, recognition, and social interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

apolis

-0.17

ocaly

-0.16

 Witness

-0.16

erview

-0.15

undles

-0.15

iversary

-0.14

Sensitive

-0.14

ukkit

-0.14

é¡Į

-0.14

ç¿Ķ

-0.14

POSITIVE LOGITS

 recognition

0.88

 Recognition

0.81

recogn

0.81

 recogn

0.76

 recognize

0.76

 recognise

0.73

Recognition

0.73

 Recogn

0.72

 recognizing

0.71

 recognizes

0.69

Activations Density 0.270%

phrases and expressions of confusion, recognition, and social interaction

No Comments

No Known Activations