INDEX

Explanations

mentions of "process" in various contexts

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

 WithEvents

-0.18

tember

-0.16

Ø§ÙĤ

-0.16

ilage

-0.16

decess

-0.15

itez

-0.15

unner

-0.14

Ð¾Ñĥ

-0.14

pas

-0.14

ece

-0.14

POSITIVE LOGITS

ional

0.33

ual

0.30

ions

0.28

(es

0.27

 itself

0.24

UAL

0.24

sing

0.23

 process

0.20

 involved

0.20

ually

0.20

Activations Density 0.048%

mentions of "process" in various contexts

No Comments

No Known Activations