INDEX

Explanations

instances of the word "share" and its variations, indicating a focus on collaboration and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

lant

-0.15

ovu

-0.15

baugh

-0.15

amat

-0.15

presso

-0.15

achment

-0.14

asis

-0.14

ÐºÐ¾ÑĤ

-0.14

owi

-0.14

eh

-0.13

POSITIVE LOGITS

_Common

0.21

 common

0.19

 responsibility

0.18

ongyang

0.17

 space

0.17

/common

0.15

çĽ¸åĲĮ

0.15

 Responsibility

0.15

cro

0.14

common

0.14

Activations Density 0.028%

instances of the word "share" and its variations, indicating a focus on collaboration and connections

No Comments

No Known Activations