INDEX

Explanations

keywords and phrases indicating winning and losing outcomes in competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ãºc

-0.15

itia

-0.15

/packages

-0.14

utin

-0.14

 Coch

-0.14

íĺĦ

-0.14

seite

-0.13

ultimate

-0.13

ÃŃ

-0.13

FRING

-0.13

POSITIVE LOGITS

 previous

0.17

 Caption

0.16

defer

0.15

chwitz

0.14

ROPERTY

0.14

 earlier

0.14

 Mata

0.14

ÅĻit

0.14

ë¦¼

0.14

 nonatomic

0.14

Activations Density 0.010%

keywords and phrases indicating winning and losing outcomes in competitive contexts

No Comments

No Known Activations