INDEX

Explanations

angles and directional positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Ð½ÑĸÑģÑĤ

-0.15

stretch

-0.15

ring

-0.15

core

-0.15

bara

-0.14

Ton

-0.14

Ð¾Ð¶

-0.14

cores

-0.14

ubern

-0.14

.metro

-0.13

POSITIVE LOGITS

 angle

0.41

 angles

0.38

angle

0.36

 Angle

0.34

-angle

0.33

incl

0.31

è§Ĵ

0.31

ob

0.31

 inclination

0.31

Angle

0.30

Activations Density 0.163%

angles and directional positioning

No Comments

No Known Activations