INDEX

Explanations

questions starting with "How."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

lier

-0.14

uger

-0.14

ocha

-0.14

urgy

-0.14

kop

-0.13

 Å¡

-0.13

 beste

-0.13

ishi

-0.13

.codes

-0.13

POSITIVE LOGITS

 long

0.21

 tall

0.21

 dÃłi

0.20

old

0.20

-old

0.19

OLD

0.19

old

0.19

do

0.19

Stuff

0.18

 often

0.18

Activations Density 0.038%

questions starting with "How."

No Comments

No Known Activations