INDEX

Explanations

expressions and metrics related to quantities or numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

reau

-0.16

alley

-0.15

ÅĻej

-0.15

bett

-0.15

rrha

-0.14

engu

-0.14

roit

-0.14

yne

-0.14

POSITIVE LOGITS

 three

0.14

.serialization

0.14

ymmetric

0.14

(CultureInfo

0.14

umer

0.14

pheric

0.13

 Tanner

0.13

 eight

0.13

 Weekly

0.13

Activations Density 0.038%

expressions and metrics related to quantities or numerical data

No Comments

No Known Activations