INDEX

Explanations

elements related to knowledge and learning traditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Canter

-0.18

#index

-0.17

aggi

-0.16

ryn

-0.16

æģ¯

-0.15

åĲ¾

-0.15

 Ø¯Ø±ÛĮ

-0.14

[NUM

-0.14

odash

-0.14

 ãĢĳ

-0.14

POSITIVE LOGITS

 redistrib

0.15

 Redistribution

0.15

 finished

0.15

 Cocoa

0.15

 cooked

0.15

 thunder

0.14

 Becker

0.14

Ib

0.13

omm

0.13

 Exped

0.13

Activations Density 0.112%

elements related to knowledge and learning traditions

No Comments

No Known Activations