INDEX

Explanations

comparative terms and concepts related to levels or degrees

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

eyi

-0.18

ongs

-0.15

ä¹Ī

-0.15

æ¥

-0.15

ØªÙĥ

-0.14

>tag

-0.14

swick

-0.14

zsche

-0.14

bie

-0.14

kr

-0.13

POSITIVE LOGITS

 thereof

0.17

 alike

0.17

 serta

0.16

odb

0.15

Î¬Î»Î¹

0.15

jar

0.15

yk

0.14

inton

0.14

/misc

0.14

 suche

0.14

Activations Density 0.067%

comparative terms and concepts related to levels or degrees

No Comments

No Known Activations