INDEX

Explanations

references to nuclear weapons and their associated risks and protocols

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

 cele

-0.15

RelativeTo

-0.14

eus

-0.14

rego

-0.14

 Bullet

-0.13

yer

-0.13

ansson

-0.13

ador

-0.13

 frail

-0.13

Pun

-0.13

POSITIVE LOGITS

edis

0.16

owi

0.16

oli

0.15

asket

0.15

wal

0.15

ooth

0.14

ãĤ¾

0.14

 sobie

0.14

 cÃ¡nh

0.14

amment

0.14

Activations Density 0.219%

references to nuclear weapons and their associated risks and protocols

No Comments

No Known Activations