INDEX

Explanations

phrases indicating actions or events that are documented or described

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

istra

-0.16

uve

-0.16

LayoutConstraint

-0.15

anos

-0.15

çĲĨçĶ±

-0.15

unik

-0.14

[__

-0.14

Ð¸ÑģÑĤÑĢÐ°

-0.14

iku

-0.14

urette

-0.14

POSITIVE LOGITS

 part

0.15

exels

0.15

Ä

0.14

 Hart

0.14

 either

0.14

ounce

0.14

 Bauer

0.14

0.13

Activations Density 0.405%

phrases indicating actions or events that are documented or described

No Comments

No Known Activations