INDEX

Explanations

technical terms and codes related to programming and software development

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

 entering

-0.17

vard

-0.15

.functions

-0.14

éĢļ

-0.14

uld

-0.14

 Wright

-0.14

iao

-0.14

eren

-0.14

Jeg

-0.13

amer

-0.13

POSITIVE LOGITS

á»¥y

0.17

umni

0.15

ango

0.14

á»¥

0.13

angep

0.13

steen

0.13

TZ

0.13

 Ð´Ð¾ÑĢ

0.13

Ãºn

0.13

umba

0.13

Activations Density 0.117%

technical terms and codes related to programming and software development

No Comments

No Known Activations