INDEX

Explanations

mathematical proofs and their outlines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

tit

-0.13

yme

-0.13

amodel

-0.13

modifiable

-0.13

 mand

-0.13

ngle

-0.13

 è¡¨

-0.13

 projects

-0.13

bic

-0.13

ALS

-0.13

POSITIVE LOGITS

 proof

0.36

 arguments

0.35

 argument

0.33

 prove

0.33

proof

0.32

Proof

0.32

_proof

0.31

è¯ģæĺİ

0.30

 Arguments

0.30

 Proof

0.30

Activations Density 0.176%

mathematical proofs and their outlines

No Comments

No Known Activations