INDEX

Explanations

terms related to obtaining or gaining possession of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ç¥

-0.14

esc

-0.14

ep

-0.14

éļª

-0.14

mv

-0.14

ight

-0.14

ãģĺ

-0.14

Pry

-0.14

 Prize

-0.14

its

-0.14

POSITIVE LOGITS

dma

0.16

Ã©gor

0.15

 dara

0.15

 filt

0.14

ildo

0.14

 NSRange

0.14

sembl

0.14

0.13

 slik

0.13

orsi

0.13

Activations Density 0.019%

terms related to obtaining or gaining possession of something

No Comments

No Known Activations