INDEX

Explanations

mathematical symbols 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 sake

-0.15

chat

-0.15

es

-0.14

 Ramos

-0.13

 wides

-0.13

asca

-0.13

egative

-0.13

pletion

-0.13

Î³Î±

-0.13

egal

-0.13

POSITIVE LOGITS

unami

0.16

leep

0.16

0.15

Ã¶ÄŁ

0.15

ussen

0.15

ippi

0.14

dale

0.14

à¸ģà¸ķ

0.14

oppers

0.14

kol

0.14

Activations Density 0.043%

mathematical symbols and notation

No Comments

No Known Activations