INDEX

Explanations

numerical data or time-related information

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

atal

-0.17

æ£ļ

-0.17

atab

-0.16

Gle

-0.15

Fog

-0.14

iej

-0.14

_mime

-0.14

ait

-0.14

 Fukushima

-0.14

asta

-0.14

POSITIVE LOGITS

ECT

0.14

tout

0.14

ET

0.14

adius

0.13

 motion

0.13

raphic

0.13

DataSet

0.13

motion

0.13

oses

0.13

/or

0.13

Activations Density 0.084%

numerical data or time-related information

No Comments

No Known Activations