INDEX

Explanations

patterns and structures within code, particularly related to regular expressions 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

 Arbor

-0.15

******↵↵

-0.15

rnek

-0.15

Î¯Î½Î·

-0.14

recogn

-0.14

olk

-0.14

Reducers

-0.14

*******↵

-0.13

inker

-0.13

{}.

-0.13

POSITIVE LOGITS

$/

0.31

/)↵

0.28

/↵

0.27

/;↵

0.27

/)

0.27

}$/

0.26

/↵↵

0.26

/i

0.25

$/,

0.25

/,

0.24

Activations Density 0.030%

patterns and structures within code, particularly related to regular expressions and error handling

No Comments

No Known Activations