INDEX

Explanations

assignment and definition statements in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

amas

-0.15

ane

-0.15

foon

-0.15

resse

-0.14

vou

-0.14

Charts

-0.13

anÃ©

-0.13

 mean

-0.13

ser

-0.13

azzi

-0.13

POSITIVE LOGITS

decltype

0.17

'=>"

0.16

ç·

0.16

ilogue

0.15

inspace

0.15

Ø´ÙħØ§ÙĦÛĮ

0.15

 Karn

0.14

_compat

0.14

ValuePair

0.14

Activations Density 0.003%

assignment and definition statements in programming code

No Comments

No Known Activations