INDEX

Explanations

bullet point symbols or icons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

otropic

-0.16

ala

-0.14

nt

-0.14

ÙĤØª

-0.14

Erd

-0.13

warts

-0.13

 mere

-0.13

ore

-0.13

mina

-0.13

ÑıÐ¶

-0.13

POSITIVE LOGITS

//{{

0.19

ï¸ı

0.18

antity

0.17

ÑģÐ¾Ð½

0.15

kest

0.15

ULER

0.14

asant

0.14

 Ø¨ÙĪØ§Ø¨Ø©

0.14

uÃŃ

0.14

antine

0.14

Activations Density 0.026%

bullet point symbols or icons

No Comments

No Known Activations