INDEX

Explanations

positive descriptions of hotel features and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 kelim

-0.18

 Blanc

-0.15

.tool

-0.15

 Mansion

-0.15

itten

-0.14

 buggy

-0.14

irut

-0.14

 cÃ´t

-0.14

ÂŃt

-0.14

-tm

-0.14

POSITIVE LOGITS

mot

0.24

 Econ

0.23

Mot

0.22

 Choice

0.19

 Extended

0.19

mot

0.18

IH

0.18

 Ð¼Ð¾ÑĤ

0.18

extended

0.18

 Budget

0.18

Activations Density 0.111%

positive descriptions of hotel features and services

No Comments

No Known Activations