INDEX

Explanations

geographical locations, such as cities, countries, and notable landmarks

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

lev

-0.14

illard

-0.14

utenberg

-0.14

ÙħØ§

-0.13

bite

-0.13

ÏģÎ¿ÏĤ

-0.13

 closely

-0.13

 tempor

-0.13

POSITIVE LOGITS

Tro

0.15

ÏģÎ¹Î±

0.15

rez

0.14

tro

0.14

Std

0.14

é¹¿

0.14

doch

0.14

ãĤµãĥ¼

0.14

ISA

0.13

oda

0.13

Activations Density 0.465%

geographical locations, such as cities, countries, and notable landmarks

No Comments

No Known Activations