INDEX

Explanations

mathematical expressions or symbols used in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

nore

-0.16

agina

-0.16

addock

-0.16

nul

-0.15

reste

-0.15

acente

-0.14

aggi

-0.14

WARE

-0.14

antz

-0.14

loor

-0.14

POSITIVE LOGITS

0.14

“

0.14

 cables

0.14

har

0.14

“

0.14

ses

0.14

Har

0.13

.processor

0.13

 them

0.13

ald

0.13

Activations Density 0.195%

mathematical expressions or symbols used in equations

No Comments

No Known Activations