INDEX

Explanations

references to legal documents and academic papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ebek

-0.14

beiter

-0.12

 detail

-0.12

UniqueId

-0.12

ublik

-0.12

gr

-0.12

 cref

-0.12

efd

-0.11

 instant

-0.11

EMPLARY

-0.11

POSITIVE LOGITS

¯¼

0.12

«ĺ

0.12

reesome

0.12

 PROGMEM

0.12

rane

0.12

Ð¾ÐºÐµ

0.12

venth

0.12

ÑıÐ±

0.12

ÙĴØ³

0.12

...↵↵↵↵

0.12

Activations Density 0.128%

references to legal documents and academic papers

No Comments

No Known Activations