INDEX

Explanations

phrases indicating uncertainty or dissatisfaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Hang

-0.16

Hang

-0.15

 pent

-0.14

 Miner

-0.14

 hang

-0.14

anca

-0.13

ä¿Ĭ

-0.13

gf

-0.13

ente

-0.13

ore

-0.13

POSITIVE LOGITS

icer

0.14

ìľ¤

0.14

sob

0.14

osti

0.14

 ders

0.14

ÑģÐ»Ð¸

0.14

ibold

0.13

 Ð·Ð°Ð½

0.13

vae

0.13

Ø§Ø¯Ø§

0.13

Activations Density 0.015%

phrases indicating uncertainty or dissatisfaction

No Comments

No Known Activations