INDEX

Explanations

mathematical notations and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Tie

-0.16

riage

-0.15

dration

-0.15

ahat

-0.14

Ã©gorie

-0.14

AndView

-0.14

èĨ

-0.14

 Tray

-0.14

azing

-0.14

ream

-0.14

POSITIVE LOGITS

tar

0.14

illard

0.14

lon

0.13

enci

0.13

wer

0.13

ÑĭÐ²Ð°

0.13

 Pest

0.13

 higher

0.13

 richt

0.13

Activations Density 0.116%

mathematical notations and equations

No Comments

No Known Activations