INDEX

Explanations

references to conspiracy and intrigue-related events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-0.15

edeki

-0.15

_usec

-0.14

 Tarif

-0.14

campo

-0.14

(Void

-0.14

onces

-0.14

alue

-0.14

 taÅŁÄ±n

-0.14

asso

-0.13

POSITIVE LOGITS

 secret

0.29

 plot

0.26

 plots

0.23

 plotting

0.22

 links

0.21

 master

0.21

 Plot

0.21

 connections

0.21

 agents

0.20

plot

0.20

Activations Density 0.287%

references to conspiracy and intrigue-related events

No Comments

No Known Activations