INDEX

Explanations

possessive pronouns and related terms indicating ownership or association

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

amat

-0.16

.ai

-0.15

GLOBALS

-0.14

uck

-0.14

\Factory

-0.14

igm

-0.13

å¤§åħ¨

-0.13

addy

-0.13

 TypeName

-0.13

çĶŁçļĦ

-0.13

POSITIVE LOGITS

 iterations

0.13

UIAlertView

0.13

 mist

0.13

wner

0.13

 Pest

0.13

 sqlCommand

0.13

kind

0.13

 Triangle

0.13

agem

0.13

obus

0.13

Activations Density 0.211%

possessive pronouns and related terms indicating ownership or association

No Comments

No Known Activations