INDEX

Explanations

proper nouns and specific identifiers related to leadership, planning, and unique references in contexts such as names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

mond

-0.15

hack

-0.15

ÙĪÛĮÙĩ

-0.14

Ð·ÑĮ

-0.14

aggio

-0.14

ÑģÑĮ

-0.14

Ø§Ø±Ùĩ

-0.13

cken

-0.13

 Liber

-0.13

ational

-0.13

POSITIVE LOGITS

xing

0.16

ãĥ©ãĥĥãĤ¯

0.14

/Game

0.14

ÎŃÎ½ÏĦ

0.14

nip

0.14

istrovstvÃŃ

0.13

apa

0.13

 assistir

0.13

.epam

0.13

 WithEvents

0.12

Activations Density 0.009%

proper nouns and specific identifiers related to leadership, planning, and unique references in contexts such as names and titles

No Comments

No Known Activations