INDEX

Explanations

references to courses or educational programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

soever

-0.19

rych

-0.17

zsche

-0.16

chy

-0.16

ated

-0.16

erdem

-0.16

opoulos

-0.15

lesen

-0.15

leich

-0.15

Ã¡bado

-0.15

POSITIVE LOGITS

ware

0.30

mates

0.22

wares

0.20

WARE

0.19

ye

0.18

ful

0.18

mate

0.18

work

0.18

Ware

0.17

yal

0.17

Activations Density 0.030%

references to courses or educational programs

No Comments

No Known Activations