INDEX

Explanations

references to digital content sharing and features related to safety, food, testing, and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

blr

-0.16

ieten

-0.15

hurst

-0.14

urre

-0.14

egade

-0.14

htub

-0.14

illard

-0.14

readcr

-0.13

sink

-0.13

CPF

-0.13

POSITIVE LOGITS

 their

0.17

Ð¾Ð½Ñĭ

0.16

 theirs

0.16

 suas

0.15

their

0.15

onen

0.14

alo

0.14

hart

0.14

 Their

0.14

ruz

0.14

Activations Density 0.098%

references to digital content sharing and features related to safety, food, testing, and regulations

No Comments

No Known Activations