INDEX

Explanations

terms related to investigations and inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ã±ana

-0.16

 appeared

-0.15

 Prev

-0.14

nat

-0.14

utut

-0.14

istrovstvÃŃ

-0.14

chn

-0.14

 formed

-0.13

 chains

-0.13

 Created

-0.13

POSITIVE LOGITS

 conducted

0.42

held

0.32

 held

0.31

 Conduct

0.29

 diá»ħn

0.28

 lasting

0.27

 Ð¿ÑĢÐ¾Ð²Ð¾Ð´

0.27

 Ø¨Ø±Ú¯Ø²Ø§Ø±

0.26

 happening

0.26

-held

0.25

Activations Density 0.069%

terms related to investigations and inquiries

No Comments

No Known Activations