INDEX

Explanations

comments in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ossier

-0.16

aura

-0.15

ASH

-0.14

MBER

-0.14

atl

-0.14

efa

-0.14

ãĥ¬ãĤ¹

-0.14

hic

-0.13

ãĥĸãĥª

-0.13

eph

-0.13

POSITIVE LOGITS

urvey

0.17

 sobie

0.15

æ¥

0.15

adin

0.15

(#)

0.15

XObject

0.15

ç«ľ

0.14

Ä±

0.14

ê·¹

0.14

OperationException

0.14

Activations Density 0.030%

comments in code

No Comments

No Known Activations