INDEX

Explanations

concepts related to booting or starting up devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ered

-0.17

rika

-0.15

itzer

-0.15

 Synopsis

-0.14

 mark

-0.14

 deportation

-0.14

losures

-0.13

bose

-0.13

/shared

-0.13

POSITIVE LOGITS

Î»Î¿ÏĤ

0.15

Fcn

0.15

adir

0.15

 Landing

0.14

 proceeds

0.14

inflate

0.13

uder

0.13

 Bilg

0.13

arend

0.13

 Ballet

0.13

Activations Density 0.026%

concepts related to booting or starting up devices

No Comments

No Known Activations