INDEX

Explanations

important nouns and significant actions related to guidance and requests

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

burgh

-0.18

çł´

-0.17

eldorf

-0.15

 Tear

-0.15

 phÃ¡

-0.15

borough

-0.14

;break

-0.14

åİĤ

-0.14

oves

-0.14

fid

-0.13

POSITIVE LOGITS

oice

0.18

roj

0.17

urga

0.17

 Dustin

0.16

Macro

0.16

å·»

0.15

slick

0.15

Ð¸Ð¶

0.14

.Store

0.14

arse

0.14

Activations Density 0.000%

important nouns and significant actions related to guidance and requests

No Comments

No Known Activations