INDEX

Explanations

mathematical expressions or symbols in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

adolu

-0.16

uard

-0.15

VERR

-0.15

apore

-0.14

pretty

-0.14

 ÙħÙĤØ±

-0.14

eref

-0.14

hai

-0.13

eric

-0.13

ferred

-0.13

POSITIVE LOGITS

wed

0.17

ingt

0.16

ing

0.16

icum

0.14

 learned

0.14

bub

0.14

Giz

0.14

ÛĮ

0.14

Activations Density 0.043%

mathematical expressions or symbols in a document

No Comments

No Known Activations