INDEX

Explanations

references to violence and violent actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

chg

-0.16

 èĥ

-0.15

à¥Īà¤²

-0.15

serter

-0.15

ãģ°

-0.15

icari

-0.15

Insensitive

-0.15

ãĥ£

-0.14

ibble

-0.14

ÑĩÑĥÐº

-0.14

POSITIVE LOGITS

-force

0.17

ernet

0.17

/or

0.15

³»

0.14

 force

0.14

lette

0.14

adier

0.14

al

0.14

force

0.14

_force

0.14

Activations Density 0.018%

references to violence and violent actions

No Comments

No Known Activations