INDEX

Explanations

phrases related to measurement and specifications

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

ãĢħ

-0.17

iske

-0.16

ilik

-0.15

yal

-0.15

ĸ

-0.15

 PROGMEM

-0.14

uary

-0.14

ROWS

-0.13

ploy

-0.13

IVER

-0.13

POSITIVE LOGITS

pto

0.14

 Bates

0.13

oop

0.13

ufs

0.13

ewire

0.13

ibbon

0.13

shima

0.13

ields

0.13

kle

0.13

Activations Density 0.225%

phrases related to measurement and specifications

No Comments

No Known Activations

phrases related to measurement and specifications

No Comments

No Known Activations