INDEX

Explanations

complex terms or concepts often associated with scientific or technical discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

è¿

-0.18

ativo

-0.17

ãĥ¡ãĥ©

-0.15

 camp

-0.14

Fry

-0.14

SHOT

-0.14

 Dickinson

-0.14

shot

-0.14

aso

-0.14

Mia

-0.14

POSITIVE LOGITS

æĸ

0.17

peria

0.16

Pek

0.15

licable

0.14

akat

0.14

fields

0.14

è±ª

0.14

áº«

0.14

usal

0.14

vo

0.14

Activations Density 0.004%

complex terms or concepts often associated with scientific or technical discussions

No Comments

No Known Activations