INDEX

Explanations

references to documentation and coding examples

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

 Worksheet

-0.13

 AndAlso

-0.13

aque

-0.13

çĹ

-0.13

Scripts

-0.13

æ®

-0.13

Ð»Ð°Ð¶

-0.13

 ÑĢÐ°Ð·ÑĢÐµÑĪ

-0.13

wordpress

-0.13

oli

-0.13

POSITIVE LOGITS

doc

0.51

 docs

0.48

 documentation

0.48

doc

0.43

documentation

0.43

Doc

0.43

Doc

0.40

Documentation

0.40

 Documentation

0.40

docs

0.40

Activations Density 0.142%

references to documentation and coding examples

No Comments

No Known Activations