INDEX

Explanations

mathematical structures and logical expressions used in formal definitions or proofs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

TOCOL

-0.17

arp

-0.16

ary

-0.15

oni

-0.15

seo

-0.14

ril

-0.14

 Bale

-0.14

Ed

-0.14

ãĤĵãģ©

-0.14

jar

-0.13

POSITIVE LOGITS

,[],

0.14

.learning

0.14

bris

0.14

 {{--<

0.14

 Escort

0.14

cee

0.13

-Javadoc

0.13

 componentDid

0.13

 slee

0.13

aec

0.13

Activations Density 0.099%

mathematical structures and logical expressions used in formal definitions or proofs

No Comments

No Known Activations