INDEX

Explanations

geolocation references and measurements related to location and navigation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

//{{

-0.15

 ká»ĥ

-0.14

 Ð´Ð°Ð²Ð½Ð¾

-0.14

Ð¾Ñī

-0.14

 seit

-0.13

 yaptÄ±ÄŁÄ±

-0.13

æĹ¢çĦ¶

-0.13

 dÃ¹

-0.13

.xtext

-0.12

amu

-0.12

POSITIVE LOGITS

 then

0.84

 before

0.84

then

0.69

before

0.69

 followed

0.68

 Then

0.65

 THEN

0.64

Then

0.61

 Before

0.58

 BEFORE

0.56

Activations Density 0.511%

geolocation references and measurements related to location and navigation

No Comments

No Known Activations