INDEX

Explanations

connections to geographic locations and routes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

owell

-0.15

mrt

-0.15

eres

-0.14

dsa

-0.14

ieur

-0.14

Ou

-0.13

 dances

-0.13

çĴ

-0.13

icorn

-0.13

elters

-0.13

POSITIVE LOGITS

ÑĤÐ°Ð¶

0.15

ojis

0.15

0.14

adero

0.14

ÏĩÎµÎ¯Î±

0.14

ogne

0.14

ikh

0.14

asi

0.14

_refl

0.13

ëıĮ

0.13

Activations Density 0.065%

connections to geographic locations and routes

No Comments

No Known Activations