INDEX

Explanations

references to tuning in to media or audio experiences

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

ucer

-0.17

imuth

-0.17

rene

-0.17

esini

-0.15

chod

-0.15

rena

-0.15

ilet

-0.15

upon

-0.14

 anzeigen

-0.14

disc

-0.14

POSITIVE LOGITS

 tuning

0.24

Tun

0.24

 fork

0.22

 tune

0.22

 Tune

0.21

 tuned

0.19

 Fork

0.19

pike

0.18

NEL

0.18

fork

0.17

Activations Density 0.010%

references to tuning in to media or audio experiences

No Comments

No Known Activations