INDEX

Explanations

instances of the word "When" in various contexts

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

aud

-0.17

veau

-0.15

voke

-0.15

cha

-0.14

ole

-0.14

React

-0.14

Pra

-0.14

Ã£o

-0.14

vert

-0.14

arin

-0.14

POSITIVE LOGITS

 GOODMAN

0.18

OwnProperty

0.16

.openg

0.15

imilar

0.14

elage

0.14

paque

0.14

elter

0.14

rane

0.13

abouts

0.13

	TokenName

0.13

Activations Density 0.040%

instances of the word "When" in various contexts

No Comments

No Known Activations