INDEX

Explanations

terms related to structure and organization in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

istrovstvÃŃ

-0.17

 Boss

-0.15

assis

-0.14

Ð¾ÑĢÐ¾Ð¼

-0.14

 Ð±Ð¾Ðº

-0.14

yre

-0.14

 ZEND

-0.13

ossier

-0.13

phins

-0.13

POSITIVE LOGITS

otti

0.16

desc

0.14

 flagged

0.14

 widest

0.14

oman

0.13

osphere

0.13

atology

0.13

 marginal

0.13

owitz

0.13

ins

0.13

Activations Density 0.031%

terms related to structure and organization in various contexts

No Comments

No Known Activations