INDEX

Explanations

programming language keywords and structures related to functions and error handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

?family

-0.14

TOTYPE

-0.13

ãĤĵãģ¨

-0.13

Ð»Ð¸ÑĪÐºÐ¾Ð¼

-0.13

Ø§Ø¦ÙĤ

-0.13

acic

-0.13

ebo

-0.13

izont

-0.13

okino

-0.12

Ãºsqueda

-0.12

POSITIVE LOGITS

 post

1.53

 Post

1.41

post

1.33

Post

1.31

-post

1.20

_post

1.16

.post

1.15

 POST

1.12

POST

1.03

(post

1.02

Activations Density 0.262%

programming language keywords and structures related to functions and error handling

No Comments

No Known Activations