INDEX

Explanations

references to coding and programming elements, particularly related to listings and annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ihan

-0.15

appen

-0.15

pop

-0.15

RLF

-0.14

iefs

-0.14

appiness

-0.14

ä¿

-0.14

venes

-0.14

amm

-0.14

aco

-0.14

POSITIVE LOGITS

 ÐļÐ°Ð±

0.16

à¸±à¸įà¸į

0.15

asca

0.14

Enlarge

0.14

wald

0.14

Ø³Ø§Ø³

0.13

deniz

0.13

BarItem

0.13

(Call

0.13

Activations Density 0.024%

references to coding and programming elements, particularly related to listings and annotations

No Comments

No Known Activations