INDEX

Explanations

instances of the word "see" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

cs

-0.18

orsi

-0.17

cai

-0.17

stem

-0.16

ly

-0.16

æ³Ĭ

-0.16

ãģĦãģ¾ãģĻ

-0.16

stk

-0.15

st

-0.15

adio

-0.15

POSITIVE LOGITS

/he

0.29

dust

0.22

 xÃ©t

0.21

-through

0.20

kest

0.19

 cref

0.19

fit

0.18

 HttpServlet

0.17

lessly

0.16

/list

0.16

Activations Density 0.112%

instances of the word "see" and its variations

No Comments

No Known Activations