INDEX

Explanations

adjectives and adverbial phrases that describe characteristics or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

unger

-0.16

 citizen

-0.15

uner

-0.14

viewer

-0.14

essenger

-0.14

rray

-0.13

celik

-0.13

ileo

-0.13

lever

-0.13

 Rays

-0.13

POSITIVE LOGITS

 TORT

0.16

endez

0.15

Ù¾Ø³

0.15

æ¾

0.14

chy

0.14

 Pall

0.14

æĸ¯çī¹

0.14

nell

0.14

 gord

0.14

ulu

0.14

Activations Density 0.004%

adjectives and adverbial phrases that describe characteristics or behaviors

No Comments

No Known Activations