INDEX

Explanations

positive feedback on businesses or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ober

-0.17

yster

-0.16

á»·

-0.14

uppe

-0.14

Ð°ÑĢÑĤ

-0.13

 Tourism

-0.13

.DependencyInjection

-0.13

thane

-0.13

 Crime

-0.13

NES

-0.13

POSITIVE LOGITS

 everything

0.17

 overall

0.16

 Everything

0.16

overall

0.14

orde

0.14

ex

0.14

uu

0.14

 frei

0.14

 experience

0.14

isson

0.14

Activations Density 0.111%

positive feedback on businesses or services

No Comments

No Known Activations