INDEX

Explanations

references to messages or themes 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Mystery

-0.18

 mystery

-0.17

iske

-0.17

uffman

-0.16

ivi

-0.16

Ã¼st

-0.16

 pairs

-0.15

 Hust

-0.15

ango

-0.15

tÃ¼

-0.14

POSITIVE LOGITS

wahl

0.16

aghan

0.16

oley

0.15

icaid

0.14

hift

0.14

lite

0.14

 ApplicationException

0.14

Úĺ

0.13

orra

0.13

Activations Density 0.017%

references to messages or themes in various contexts

No Comments

No Known Activations