INDEX

Explanations

references to competitive events or contests

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ighton

-0.17

 nackte

-0.17

alin

-0.16

cratch

-0.15

ergy

-0.15

itten

-0.14

Scoped

-0.14

ÑĢÐ¾Ð¹

-0.14

braco

-0.14

POSITIVE LOGITS

gc

0.17

apyrus

0.17

orest

0.15

ÐµÑĨ

0.15

engu

0.14

æ´

0.14

.gc

0.14

izzer

0.13

 Peripheral

0.13

zy

0.13

Activations Density 0.003%

references to competitive events or contests

No Comments

No Known Activations