INDEX

Explanations

references to supernatural beings or events

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

yg

-0.17

 Gods

-0.16

EATURE

-0.16

cheme

-0.15

zos

-0.14

ungle

-0.14

rex

-0.13

scheme

-0.13

 Kramer

-0.13

 offending

-0.13

POSITIVE LOGITS

EVP

0.26

 paranormal

0.23

 ghost

0.23

Ghost

0.21

 Ghost

0.19

éľĬ

0.19

 phantom

0.18

ghost

0.18

 spirits

0.18

geist

0.17

Activations Density 0.027%

references to supernatural beings or events

No Comments

No Known Activations