INDEX

Explanations

personal experiences and reflections

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

arLayout

-0.17

jer

-0.15

umbn

-0.14

 rast

-0.14

tha

-0.14

 addCriterion

-0.14

wor

-0.13

 Ð±ÑĢÐ¾Ñģ

-0.13

Þ

-0.13

_throw

-0.13

POSITIVE LOGITS

keit

0.16

fol

0.16

ourcem

0.15

ample

0.15

 Ø¨Ø·

0.15

urge

0.15

Ä©nh

0.15

inters

0.14

adm

0.14

unger

0.14

Activations Density 0.009%

personal experiences and reflections

No Comments

No Known Activations