INDEX

Explanations

mathematical terms and symbols related to theorems and proofs in advanced theoretical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

omite

-0.15

hap

-0.15

 horse

-0.15

 Sloan

-0.15

csi

-0.15

GM

-0.14

 compliments

-0.14

 Stef

-0.14

ilan

-0.14

POSITIVE LOGITS

 fusion

0.22

 Fusion

0.21

 Pain

0.21

fusion

0.21

Zam

0.20

Vir

0.20

Vir

0.20

 integr

0.19

 Vertex

0.19

fuse

0.18

Activations Density 0.038%

mathematical terms and symbols related to theorems and proofs in advanced theoretical concepts

No Comments

No Known Activations