INDEX

Explanations

references to locations, particularly in a geographical context

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

obuf

-0.16

angep

-0.15

obra

-0.15

 NavParams

-0.15

 CHAPTER

-0.15

iddet

-0.15

wine

-0.14

roman

-0.14

 Shared

-0.13

åĭĻ

-0.13

POSITIVE LOGITS

lio

0.17

mo

0.15

elsing

0.14

aze

0.14

URN

0.13

igel

0.13

presso

0.13

scp

0.13

ucene

0.13

ible

0.13

Activations Density 0.339%

references to locations, particularly in a geographical context

No Comments

No Known Activations