INDEX

Explanations

references to firearms and shooting incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.18

-0.16

agi

-0.16

 tick

-0.15

 knife

-0.15

loi

-0.15

vard

-0.14

vig

-0.14

oller

-0.14

lya

-0.14

POSITIVE LOGITS

 shots

0.25

 shot

0.23

shots

0.21

-shot

0.20

 discharge

0.19

 blanks

0.19

 volley

0.18

 fired

0.18

 Shots

0.18

shot

0.17

Activations Density 0.054%

references to firearms and shooting incidents

No Comments

No Known Activations