INDEX

Explanations

mentions of safety features related to automobiles and crash testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

perms

-0.20

rna

-0.15

usercontent

-0.15

maal

-0.14

 Seal

-0.14

DebugEnabled

-0.14

REFERENCE

-0.14

Ð²Ð°Ð²

-0.14

qd

-0.14

ffen

-0.13

POSITIVE LOGITS

 safety

0.16

 accord

0.14

Cov

0.14

 structural

0.14

.showMessageDialog

0.14

car

0.14

 sire

0.13

Mat

0.13

 Safety

0.13

encent

0.13

Activations Density 0.016%

mentions of safety features related to automobiles and crash testing

No Comments

No Known Activations