INDEX

Explanations

mathematical notation and elements within formal proofs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

iej

-0.15

/cgi

-0.15

\/\/

-0.14

 Ð¿Ð¾Ð²ÐµÑĢ

-0.14

izzo

-0.14

 æĸ

-0.14

__,__

-0.13

querque

-0.13

ature

-0.13

æĸ

-0.13

POSITIVE LOGITS

 Lust

0.15

 PACKET

0.15

gol

0.15

Gol

0.14

 shakes

0.14

 Robertson

0.14

 Brand

0.14

 rides

0.14

 singly

0.13

tering

0.13

Activations Density 0.474%

mathematical notation and elements within formal proofs

No Comments

No Known Activations