INDEX

Explanations

numerical data points and episode identifiers

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

ynes

-0.21

 "../../../../

-0.16

iii

-0.15

_third

-0.15

 Saturdays

-0.15

III

-0.15

 fourth

-0.14

_stride

-0.14

Rod

-0.14

 Saturday

-0.14

POSITIVE LOGITS

âĳ¡

0.40

0.35

0.33

Feb

0.32

0.31

 February

0.30

åįģäºĮ

0.30

Activations Density 0.139%

numerical data points and episode identifiers

No Comments

No Known Activations