INDEX

Explanations

tokens related to emotions or loyalty in a specific language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

_exempt

-0.17

orate

-0.16

ovÃ¡

-0.15

Õ¡Õ

-0.15

lette

-0.15

ova

-0.14

Gur

-0.14

EATURE

-0.14

imated

-0.13

ebb

-0.13

POSITIVE LOGITS

erva

0.16

_literals

0.15

à¸Ńà¸Ļà¸Ķ

0.14

insula

0.14

ãģıãĤī

0.14

ibs

0.13

etre

0.13

Ð¿Ðµ

0.13

 SHARES

0.13

Activations Density 0.007%

tokens related to emotions or loyalty in a specific language

No Comments

No Known Activations