INDEX

Explanations

nouns or plural subjects related to people, items, or entities

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

avery

-0.14

 antennas

-0.14

 Shock

-0.14

iT

-0.14

 Ð¾Ð¿

-0.14

eft

-0.14

 labore

-0.14

THR

-0.13

enus

-0.13

 poil

-0.13

POSITIVE LOGITS

 Offset

0.16

Ã¼b

0.15

agal

0.15

ulla

0.15

argon

0.15

ectl

0.15

ÑĮ

0.14

âĦĸâĦĸ

0.14

ALSE

0.14

iddy

0.14

Activations Density 0.009%

nouns or plural subjects related to people, items, or entities

No Comments

No Known Activations