INDEX

Explanations

numerical data and statistics related to competitions or events

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

urname

-0.16

Î³Î³ÎµÎ»

-0.16

taire

-0.15

eten

-0.15

ingly

-0.15

atron

-0.15

izon

-0.15

 Rings

-0.15

omination

-0.14

rade

-0.14

POSITIVE LOGITS

0.14

transparent

0.14

èĪĪ

0.14

 Freund

0.14

ampus

0.14

ropa

0.14

casecmp

0.14

à¤¾à¤ĩà¤²

0.13

%;">

0.13

 ÐŀÑģÑĤ

0.13

Activations Density 0.028%

numerical data and statistics related to competitions or events

No Comments

No Known Activations