INDEX

Explanations

references to individuals' careers and achievements in the entertainment industry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

odel

-0.15

lyph

-0.15

.sponge

-0.14

wsz

-0.14

å±Ĭ

-0.14

 swallow

-0.14

Intro

-0.14

 sÃ¢u

-0.14

avel

-0.13

urus

-0.13

POSITIVE LOGITS

 rose

0.28

rose

0.24

 rocket

0.19

aname

0.19

 burst

0.19

Rose

0.18

bec

0.18

 rise

0.18

 carved

0.18

 Rose

0.18

Activations Density 0.115%

references to individuals' careers and achievements in the entertainment industry

No Comments

No Known Activations