INDEX

Explanations

dates and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ocking

-0.16

alam

-0.15

ãĤµãĥ¼

-0.15

cco

-0.14

athers

-0.14

esser

-0.14

ion

-0.14

agi

-0.14

-0.13

ohl

-0.13

POSITIVE LOGITS

/ts

0.15

Ð°Ð½Ð¸ÑĨ

0.15

 Hyde

0.14

uez

0.13

isor

0.13

ependency

0.13

 Yates

0.13

iske

0.13

mil

0.13

 onView

0.13

Activations Density 0.099%

dates and numerical data

No Comments

No Known Activations