INDEX

Explanations

references to murder and violent crimes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ird

-0.16

-0.15

uto

-0.14

lage

-0.14

_corners

-0.14

ê¸ī

-0.14

ileo

-0.14

åĬŁ

-0.14

late

-0.13

POSITIVE LOGITS

ously

0.25

ous

0.23

abilia

0.22

-su

0.20

 spree

0.18

emek

0.17

esses

0.17

alla

0.16

joy

0.16

 rate

0.15

Activations Density 0.014%

references to murder and violent crimes

No Comments

No Known Activations