INDEX

Explanations

programming or coding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

askan

-0.18

 RaycastHit

-0.16

arin

-0.15

owl

-0.15

Ø§Ø±Ùģ

-0.14

arem

-0.14

æĬ

-0.14

oldem

-0.14

 PartialView

-0.13

ook

-0.13

POSITIVE LOGITS

 rods

0.27

rod

0.23

Rod

0.21

Rod

0.17

_COLL

0.16

Obj

0.16

 rule

0.15

 Grid

0.15

 grid

0.15

_PI

0.15

Activations Density 0.000%

programming or coding elements

No Comments

No Known Activations