INDEX

Explanations

references to specific television shows and movies

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

adro

-0.17

ipi

-0.16

azzo

-0.15

 Kendrick

-0.15

zag

-0.15

ìģ

-0.15

iggers

-0.15

ÃŃsk

-0.14

Tracker

-0.14

çĳŁ

-0.14

POSITIVE LOGITS

 synd

0.24

 segments

0.19

 Mutual

0.19

 program

0.18

 sponsors

0.18

 Synd

0.18

 segment

0.17

 Program

0.17

 show

0.17

 programs

0.17

Activations Density 0.118%

references to specific television shows and movies

No Comments

No Known Activations