INDEX

Explanations

instances of the phrase "in" followed by a variety of 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

iyim

-0.17

aire

-0.17

ÑĢÐ°Ðº

-0.16

aber

-0.15

SHARE

-0.15

Ã¡nd

-0.15

ISC

-0.15

onth

-0.15

mos

-0.15

POSITIVE LOGITS

Äįi

0.15

eri

0.15

 pathMatch

0.14

lio

0.14

tero

0.14

uft

0.13

 Lone

0.13

llll

0.13

ns

0.13

Lis

0.13

Activations Density 0.010%

instances of the phrase "in" followed by a variety of contexts

No Comments

No Known Activations