INDEX

Explanations

terms related to threat or risk

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

tle

-0.15

erez

-0.15

ì°¨

-0.14

ãģ¡ãĤĩ

-0.14

uffers

-0.14

Äįan

-0.14

éĢł

-0.14

éĻµ

-0.14

RenderTarget

-0.14

å±

-0.14

POSITIVE LOGITS

ously

0.33

ous

0.33

-danger

0.22

éļª

0.22

oust

0.20

rous

0.20

osity

0.20

éĻ©

0.20

 zone

0.18

OUS

0.18

Activations Density 0.023%

terms related to threat or risk

No Comments

No Known Activations