INDEX

Explanations

words related to numerical values or quantities in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ering

-0.17

íģ¼

-0.15

arity

-0.15

IRROR

-0.15

brief

-0.15

usercontent

-0.15

createForm

-0.14

ä¸įåĪ°

-0.14

lemen

-0.13

POSITIVE LOGITS

 travÃ©s

0.18

arah

0.16

anas

0.16

speed

0.15

usz

0.14

ingle

0.14

ÑıÐ¼Ð¸

0.14

ÙħÙĦØ©

0.14

sid

0.14

 partir

0.14

Activations Density 0.029%

words related to numerical values or quantities in a context

No Comments

No Known Activations