INDEX

Explanations

references to interviews and press releases related to media coverage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

exels

-0.16

 Duck

-0.15

iqu

-0.14

bbc

-0.14

ABC

-0.14

 VÅ¡

-0.14

 prze

-0.14

erate

-0.14

ç²¾åĵģ

-0.13

éŀĭ

-0.13

POSITIVE LOGITS

 Variety

0.31

 Collider

0.30

THR

0.29

 Deadline

0.28

Vari

0.28

 Entertainment

0.26

Collider

0.26

EW

0.26

Deadline

0.25

 variety

0.25

Activations Density 0.088%

references to interviews and press releases related to media coverage

No Comments

No Known Activations