INDEX

Explanations

references to research and academic collaborations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

áº¿

-0.16

 Hund

-0.14

ecl

-0.14

 Angiospermae

-0.14

&E

-0.13

 isolated

-0.13

.robot

-0.13

ajas

-0.13

IFS

-0.13

.Func

-0.13

POSITIVE LOGITS

-archive

0.21

 imagin

0.21

 spaces

0.20

 tempor

0.20

 affect

0.19

spaces

0.19

 raced

0.19

 Archive

0.19

/memory

0.18

_spaces

0.18

Activations Density 0.183%

references to research and academic collaborations

No Comments

No Known Activations