INDEX

Explanations

quantitative data and statistics related to various topics

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

Ã©sz

-0.16

grese

-0.14

 vess

-0.14

Ã¼cken

-0.14

 rÃ¨

-0.14

ysz

-0.13

TouchUpInside

-0.13

 taller

-0.13

 activity

-0.13

 traverse

-0.13

POSITIVE LOGITS

Extern

0.17

HELL

0.15

pga

0.15

 Ø¯Ø§Ùħ

0.14

 ÐľÑĸÐ½ÑĸÑģÑĤÐµÑĢ

0.14

¼

0.14

idd

0.14

çłĶç©¶æīĢ

0.14

æŁ´

0.14

Ø§ØŃØª

0.14

Activations Density 0.298%

quantitative data and statistics related to various topics

No Comments

No Known Activations