INDEX

Explanations

programming and technical concepts related to data processing and validation

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

iets

-0.16

IFI

-0.15

_plural

-0.14

è¾

-0.13

auss

-0.13

plers

-0.13

Ø§Ø¹ÙĬØ©

-0.13

Ø²Ùħ

-0.13

ÑĪÐºÐ°

-0.13

eax

-0.13

POSITIVE LOGITS

ase

0.16

erto

0.15

Ð»Ð°Ð¶

0.15

gain

0.13

oms

0.13

eria

0.13

 Hearth

0.13

alcon

0.13

 glide

0.13

gg

0.13

Activations Density 0.011%

programming and technical concepts related to data processing and validation

No Comments

No Known Activations