INDEX

Explanations

programming-related terms and structures, particularly those associated with functions, variables, and data management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

LastError

-0.16

()?;↵

-0.14

().

-0.14

>().

-0.14

 ();↵

-0.14

GREE

-0.14

antor

-0.14

vice

-0.14

ythe

-0.14

_();↵

-0.14

POSITIVE LOGITS

=None

0.24

=null

0.24

):↵

0.21

):↵↵

0.18

)↵

0.18

):

0.17

){↵

0.17

=NULL

0.16

){↵↵

0.16

Activations Density 0.155%

programming-related terms and structures, particularly those associated with functions, variables, and data management

No Comments

No Known Activations