INDEX

Explanations

references to murder and related violent acts

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

Ð²Ð°ÑĢ

-0.17

 Thief

-0.15

lage

-0.15

htt

-0.14

_corners

-0.14

nie

-0.14

unes

-0.14

imate

-0.14

eward

-0.14

POSITIVE LOGITS

ously

0.33

ous

0.28

abilia

0.25

esses

0.23

-su

0.21

 mystery

0.20

 spree

0.20

OUS

0.20

pedia

0.18

 scene

0.18

Activations Density 0.016%

references to murder and related violent acts

No Comments

No Known Activations