INDEX

Explanations

details related to dining and hotel features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

immel

-0.16

jeta

-0.15

.BorderColor

-0.14

hydr

-0.14

idelberg

-0.14

Ð¾ÑıÐ½

-0.14

erson

-0.14

 adipiscing

-0.13

itbart

-0.13

sumer

-0.13

POSITIVE LOGITS

 complimentary

0.20

 wired

0.19

.Feature

0.18

 Wired

0.17

 Featured

0.16

Cri

0.15

cri

0.15

AMENT

0.15

va

0.15

 mult

0.15

Activations Density 0.009%

details related to dining and hotel features

No Comments

No Known Activations