INDEX

Explanations

elements related to instructional content or guides

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

çĴ

-0.16

ountains

-0.15

 ãĢľ

-0.14

Ã²ng

-0.14

nam

-0.14

ould

-0.14

isure

-0.13

avar

-0.13

 intval

-0.13

ãĤ

-0.13

POSITIVE LOGITS

ikip

0.14

ENN

0.14

Wet

0.14

oling

0.14

_{}

0.13

ode

0.13

fds

0.13

apolis

0.13

wet

0.13

aka

0.13

Activations Density 0.108%

elements related to instructional content or guides

No Comments

No Known Activations