INDEX

Explanations

instances of the word "incorporate" and related variations

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

zure

-0.15

etter

-0.14

.grp

-0.14

ern

-0.14

earing

-0.13

Ð²Ð¾Ð´

-0.13

DMI

-0.13

à¤¸à¤¨

-0.13

packed

-0.13

èĦ±

-0.13

POSITIVE LOGITS

 into

0.20

isine

0.19

Into

0.17

 Into

0.17

 incorpor

0.17

into

0.16

hes

0.16

 vÃło

0.15

_Framework

0.14

ìĻ¸

0.14

Activations Density 0.037%

instances of the word "incorporate" and related variations

No Comments

No Known Activations