INDEX

Explanations

numeric data or measurements in a dataset

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

iji

-0.15

-0.14

ex

-0.14

ynos

-0.14

BO

-0.14

fab

-0.13

cad

-0.13

 rocking

-0.13

el

-0.13

POSITIVE LOGITS

ä»ª

0.16

.dp

0.15

åĦĢ

0.14

ãĥ³ãĥĲ

0.14

Ø´Ùĩ

0.14

ncia

0.13

LOAT

0.13

 Reich

0.13

fro

0.13

cken

0.13

Activations Density 0.004%

numeric data or measurements in a dataset

No Comments

No Known Activations