INDEX

Explanations

references to lists, schedules, and achievements related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

emos

-0.20

assic

-0.18

reich

-0.16

aign

-0.16

assin

-0.16

yg

-0.15

EO

-0.15

ients

-0.15

reo

-0.15

roup

-0.15

POSITIVE LOGITS

 HERE

0.17

 below

0.14

 scar

0.14

 here

0.14

Ze

0.14

áº¡t

0.14

Wak

0.14

Zak

0.14

 Plymouth

0.14

ota

0.14

Activations Density 0.108%

references to lists, schedules, and achievements related to various topics

No Comments

No Known Activations