INDEX

Explanations

phrases related to educational programs and affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

errupt

-0.14

ColumnType

-0.14

aphore

-0.14

ZX

-0.13

WC

-0.13

ibling

-0.13

WC

-0.13

zs

-0.13

DX

-0.13

elocity

-0.13

POSITIVE LOGITS

CN

0.29

Sor

0.27

-CN

0.25

 Labor

0.24

 Univers

0.24

 Mines

0.24

 Pole

0.23

CN

0.23

INS

0.23

ENS

0.23

Activations Density 0.041%

phrases related to educational programs and affiliations

No Comments

No Known Activations