INDEX

Explanations

geographic locations and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ensi

-0.16

SearchTree

-0.15

 Residents

-0.15

_pb

-0.14

led

-0.14

usher

-0.14

sez

-0.14

 Rich

-0.14

 Pregn

-0.13

 residents

-0.13

POSITIVE LOGITS

.userInteractionEnabled

0.17

 located

0.16

jÃŃ

0.16

 location

0.15

usu

0.15

 ìľĦì¹ĺ

0.15

abric

0.14

oso

0.14

Location

0.14

Activations Density 0.304%

geographic locations and their descriptions

No Comments

No Known Activations