INDEX

Explanations

programming commands and their outputs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 bleach

-0.15

oj

-0.14

 plain

-0.14

Ost

-0.14

acho

-0.14

vic

-0.14

aping

-0.14

ble

-0.14

ref

-0.13

addColumn

-0.13

POSITIVE LOGITS

umb

0.18

ustum

0.16

illet

0.16

UMB

0.16

orgh

0.16

FullScreen

0.15

INLINE

0.15

æ½ľ

0.15

erli

0.15

 stripslashes

0.14

Activations Density 0.001%

programming commands and their outputs

No Comments

No Known Activations