INDEX

Explanations

details related to spatial relationships and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Demp

-0.16

emain

-0.15

enz

-0.15

WithPath

-0.14

 escorts

-0.14

_PM

-0.14

ering

-0.14

phem

-0.13

mith

-0.13

pm

-0.13

POSITIVE LOGITS

arges

0.15

spread

0.14

egl

0.14

intree

0.14

 Spread

0.14

 Serif

0.14

.simps

0.14

Spread

0.14

nes

0.14

Activations Density 0.047%

details related to spatial relationships and measurements

No Comments

No Known Activations