INDEX

Explanations

the prefix "de-" indicating reversal or removal of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

asca

-0.17

anki

-0.17

cob

-0.16

allah

-0.14

 bells

-0.14

rikes

-0.14

 Ð´ÐµÐ»Ð¾

-0.14

èĩº

-0.13

gow

-0.13

POSITIVE LOGITS

ĶåĽŀ

0.20

eer

0.17

ercul

0.16

irsch

0.15

oreach

0.15

Łèĥ½

0.15

arda

0.15

/gpl

0.15

Æ°Æ¡ng

0.15

ery

0.15

Activations Density 0.026%

the prefix "de-" indicating reversal or removal of something

No Comments

No Known Activations