INDEX

Explanations

instances of the word "just" and variations of the verb "be."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ulaire

-0.15

>tag

-0.15

ntag

-0.15

ynthesis

-0.15

emarks

-0.15

ewidth

-0.15

esis

-0.14

 è©

-0.14

Gee

-0.14

elay

-0.14

POSITIVE LOGITS

å§ĵ

0.17

acey

0.16

bara

0.15

andes

0.14

åįĢ

0.14

-Jun

0.13

uso

0.13

 Karlov

0.13

ÑĮÐºÐ¾

0.13

warts

0.13

Activations Density 0.017%

instances of the word "just" and variations of the verb "be."

No Comments

No Known Activations