INDEX

Explanations

references to document formats and types of media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

orgh

-0.15

*ft

-0.15

unic

-0.15

 Kimber

-0.14

agi

-0.14

ãģĽ

-0.14

ONTAL

-0.13

ç·Ĵ

-0.13

inters

-0.13

 Ø¯Ø§Ùħ

-0.13

POSITIVE LOGITS

.mit

0.18

reta

0.17

rena

0.15

cimal

0.15

anel

0.15

ãĥ³ãĥĶ

0.14

ikki

0.14

irket

0.14

 condition

0.14

Activations Density 0.200%

references to document formats and types of media

No Comments

No Known Activations