INDEX

Explanations

references to book titles and their details

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

olas

-0.17

legg

-0.17

elow

-0.16

é§

-0.16

nal

-0.14

 soud

-0.14

oku

-0.14

Ð¸ÑĤÐµÐ»ÑĮÐ½Ð¾ÑģÑĤÑĮ

-0.14

edom

-0.14

itzer

-0.14

POSITIVE LOGITS

ijke

0.16

apesh

0.16

vit

0.15

toFloat

0.15

Î¼Î²

0.15

enheim

0.15

hausen

0.14

vit

0.14

akan

0.13

.win

0.13

Activations Density 0.009%

references to book titles and their details

No Comments

No Known Activations