INDEX

Explanations

phrases that express evaluations or statements about experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

hip

-0.18

borg

-0.16

hle

-0.15

ockets

-0.14

CTS

-0.14

 strict

-0.14

ater

-0.14

 haus

-0.13

leground

-0.13

POSITIVE LOGITS

ande

0.17

ars

0.15

Ð»Ñİ

0.15

esini

0.14

emann

0.14

 chore

0.13

Ú¯Ø§ÙĨÛĮ

0.13

ARS

0.13

-navbar

0.13

Activations Density 0.021%

phrases that express evaluations or statements about experiences

No Comments

No Known Activations