INDEX

Explanations

terms related to security and protection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

erdale

-0.18

able

-0.16

omor

-0.15

eras

-0.14

htub

-0.14

suma

-0.14

anca

-0.14

ings

-0.14

era

-0.14

POSITIVE LOGITS

istically

0.20

 pÃ¡s

0.16

inally

0.16

ologically

0.16

astically

0.15

 ÐºÑĢÑĭ

0.15

 ByVal

0.15

 igen

0.14

ify

0.14

TON

0.14

Activations Density 0.458%

terms related to security and protection

No Comments

No Known Activations