INDEX

Explanations

references to guns and firearms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ÐµÑĢÐ¸Ð½

-0.19

HORT

-0.16

cin

-0.15

gor

-0.15

hra

-0.15

ØªÙĨ

-0.15

hid

-0.15

crast

-0.15

oha

-0.15

tte

-0.14

POSITIVE LOGITS

pow

0.32

metal

0.24

ned

0.24

ning

0.23

shots

0.23

play

0.22

ny

0.21

boat

0.20

fight

0.20

smith

0.20

Activations Density 0.023%

references to guns and firearms

No Comments

No Known Activations