INDEX

Explanations

programming syntax and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

**,

-0.16

osl

-0.14

emm

-0.14

eniable

-0.14

unate

-0.14

{},

-0.14

apus

-0.13

 Ð¾ÑĩÐµÑĢÐµÐ´

-0.13

Ã¶r

-0.13

//_

-0.13

POSITIVE LOGITS

.*

0.34

.*

0.31

.+

0.29

(\

0.29

([^

0.27

([\

0.26

[\

0.25

.*?)

0.24

(?:

0.23

\s

0.23

Activations Density 0.066%

programming syntax and structure

No Comments

No Known Activations