INDEX

Explanations

terms related to weaponry and explosive devices

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

 coils

-0.15

zte

-0.15

 signals

-0.15

arella

-0.14

Sac

-0.14

 Bald

-0.14

 abst

-0.14

 signal

-0.14

pub

-0.14

POSITIVE LOGITS

 shock

0.22

 deton

0.21

 Shock

0.19

Shock

0.18

 blast

0.18

 ÑĥÐ´Ð°ÑĢ

0.18

blast

0.17

 Glas

0.17

ignet

0.17

mun

0.17

Activations Density 0.048%

terms related to weaponry and explosive devices

No Comments

No Known Activations