INDEX

Explanations

abbreviations and acronyms related to organizations and professions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

erras

-0.17

 Adolf

-0.15

Ã³c

-0.15

verbosity

-0.14

é¡¿

-0.14

verte

-0.14

 à¤ļà¤²

-0.14

Gus

-0.14

oil

-0.14

CLUD

-0.14

POSITIVE LOGITS

aine

0.15

 jack

0.14

egr

0.14

idders

0.13

 JACK

0.13

 Sparks

0.13

allo

0.13

itten

0.13

ÐµÐ½Ñĥ

0.13

baj

0.13

Activations Density 0.043%

abbreviations and acronyms related to organizations and professions

No Comments

No Known Activations