INDEX

Explanations

mathematical concepts related to proofs and theorems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

amodel

-0.16

rtype

-0.14

ivent

-0.14

Ð¼Ð°Ð·

-0.13

 models

-0.13

.apple

-0.13

ories

-0.13

 Models

-0.13

_Parms

-0.13

.Physics

-0.13

POSITIVE LOGITS

 proof

0.39

 lemma

0.35

 Lemma

0.32

 proofs

0.32

 Proof

0.31

 prove

0.30

proof

0.29

è¯ģæĺİ

0.29

lemma

0.28

 proving

0.28

Activations Density 0.269%

mathematical concepts related to proofs and theorems

No Comments

No Known Activations