INDEX

Explanations

questions that begin 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

undy

-0.17

idar

-0.16

 Ø¯Ø§Ø´ØªÙĨØ¯

-0.15

esa

-0.15

-urlencoded

-0.14

ÃŃrk

-0.14

stÅĻÃŃ

-0.14

/rss

-0.14

[array

-0.14

imating

-0.14

POSITIVE LOGITS

do

0.32

am

0.22

can

0.22

ewn

0.21

dy

0.20

 come

0.19

do

0.19

 should

0.19

di

0.18

 shall

0.18

Activations Density 0.033%

questions that begin with "How."

No Comments

No Known Activations