INDEX

Explanations

elements relating to improvements or options in design

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

\:

-0.17

wik

-0.16

arem

-0.15

 Mant

-0.15

ometry

-0.15

 Dion

-0.14

ingen

-0.14

Ë

-0.14

wei

-0.14

ear

-0.13

POSITIVE LOGITS

ÏģÎ¿Ïħ

0.17

Ľ°

0.14

RIX

0.14

ancellable

0.14

ÏģÎ±ÏĤ

0.14

ÏĨÎ·

0.13

 heat

0.13

 PureComponent

0.13

ITAL

0.13

 Bulls

0.13

Activations Density 0.057%

elements relating to improvements or options in design

No Comments

No Known Activations