INDEX

Explanations

programming constructs and syntax, particularly related to object-oriented programming and class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ongs

-0.17

 latter

-0.16

ints

-0.15

ãĥŀ

-0.14

ãĤ¢

-0.14

/how

-0.14

arel

-0.14

Ã¶k

-0.14

fos

-0.14

-0.13

POSITIVE LOGITS

oyer

0.17

ĻĤ

0.16

npos

0.15

YLeaf

0.15

osate

0.15

liament

0.15

ipp

0.14

*)(

0.14

pton

0.14

eday

0.14

Activations Density 0.013%

programming constructs and syntax, particularly related to object-oriented programming and class definitions

No Comments

No Known Activations