INDEX

Explanations

mathematical terms and concepts related to proofs and lemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Ster

-0.14

vd

-0.14

 Interr

-0.14

vette

-0.14

-errors

-0.14

Î³Î½Ïī

-0.14

uslim

-0.13

mas

-0.13

 cons

-0.13

POSITIVE LOGITS

ARB

0.18

agara

0.17

 POINTER

0.17

ÙĪØ±Ø§

0.16

arda

0.15

steder

0.15

Ã´n

0.15

 cannot

0.15

woff

0.14

Ð¾ÑĢÐ¾

0.14

Activations Density 0.125%

mathematical terms and concepts related to proofs and lemmas

No Comments

No Known Activations