INDEX

Explanations

expressions of quantity and intensity in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 DISCLAIM

-0.17

ranÃŃ

-0.14

adir

-0.14

anik

-0.14

oad

-0.14

adius

-0.14

 ControllerBase

-0.14

OAD

-0.14

avana

-0.14

EDIA

-0.14

POSITIVE LOGITS

TOO

0.25

-too

0.23

too

0.23

too

0.23

Too

0.22

Too

0.21

å¤ª

0.19

 ÑģÐ»Ð¸ÑĪÐºÐ¾Ð¼

0.17

etti

0.16

 å¤ª

0.16

Activations Density 0.138%

expressions of quantity and intensity in descriptions

No Comments

No Known Activations