INDEX

Explanations

mathematical expressions and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

XMLElement

-0.19

ahren

-0.16

kelig

-0.15

rike

-0.15

SWG

-0.15

ÌĨ

-0.15

ennes

-0.15

phan

-0.14

arde

-0.14

PCP

-0.14

POSITIVE LOGITS

 destabil

0.16

 Strait

0.15

 ÙħØ¨

0.14

 anchors

0.14

ryn

0.14

 Lange

0.14

COR

0.13

ichert

0.13

ears

0.13

Activations Density 0.134%

mathematical expressions and notation

No Comments

No Known Activations