INDEX

Explanations

specific geographical locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

alley

-0.14

Ð½ÑĸÑģÑĤÑİ

-0.14

isel

-0.14

oster

-0.14

olland

-0.14

Ã¡zd

-0.14

asca

-0.13

\/\/

-0.13

Å¡k

-0.13

rew

-0.13

POSITIVE LOGITS

edException

0.15

ibri

0.14

Ð»Ð°Ð²Ð°

0.14

 ++↵

0.14

ķ

0.13

 clearColor

0.13

ÑĢÑĥÐ¿Ð¿

0.13

rak

0.13

Ã¤ÃŁ

0.13

Activations Density 0.186%

specific geographical locations and institutions

No Comments

No Known Activations