INDEX

Explanations

references to personal journeys and experiences related to travel

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

fare

-0.16

 further

-0.16

AccessType

-0.15

rych

-0.15

 deep

-0.15

oksen

-0.14

ingham

-0.14

ched

-0.14

.deep

-0.14

eldon

-0.14

POSITIVE LOGITS

ĥģ

0.15

rek

0.15

éĺ´

0.14

Pie

0.14

eru

0.14

.MSG

0.14

adj

0.13

ÐµÐºÑĤÐ¸

0.13

ÙİÙĪ

0.13

Activations Density 0.063%

references to personal journeys and experiences related to travel

No Known Activations