INDEX

Explanations

references to aspects of architecture and structural descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 ÃĩaÄŁ

-0.18

 Packing

-0.15

 antid

-0.14

Facade

-0.14

ozilla

-0.14

pires

-0.13

olls

-0.13

ç·´

-0.13

ymax

-0.13

Hin

-0.13

POSITIVE LOGITS

 Lenin

0.20

 Linden

0.17

Object

0.17

sob

0.16

sok

0.16

 ensemble

0.15

 Push

0.15

 objekt

0.15

object

0.15

ãĤĤãģ£ãģ¨

0.15

Activations Density 0.129%

references to aspects of architecture and structural descriptions

No Comments

No Known Activations