INDEX

Explanations

technical specifications and descriptions of components in a mechanical or surgical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

æŀ¶

-0.20

 poles

-0.17

/trunk

-0.16

 zoom

-0.15

 angled

-0.15

ÑıÑģ

-0.14

ãĥ¼ãĥª

-0.14

 spindle

-0.14

akis

-0.14

 axial

-0.14

POSITIVE LOGITS

 slots

0.22

gro

0.21

Gro

0.20

 cham

0.20

gro

0.20

Gro

0.19

 Conc

0.19

 bosses

0.19

tab

0.18

 groove

0.18

Activations Density 0.200%

technical specifications and descriptions of components in a mechanical or surgical context

No Comments

No Known Activations