INDEX

Explanations

elements related to numerical or significant data values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ConverterFactory

-0.16

lein

-0.16

erra

-0.15

sville

-0.14

Ã»

-0.14

kees

-0.14

vanced

-0.14

á¿¦

-0.14

uman

-0.14

 Affero

-0.14

POSITIVE LOGITS

 diversity

0.17

Pur

0.17

 Diversity

0.16

Bar

0.15

).__

0.15

 purity

0.14

.GroupLayout

0.14

LabelText

0.14

 Variety

0.14

BarButton

0.14

Activations Density 0.009%

elements related to numerical or significant data values

No Comments

No Known Activations

elements related to numerical or significant data values

No Comments

No Known Activations