INDEX

Explanations

code-related terminologies and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

inati

-0.15

okrat

-0.15

pery

-0.14

ì§Ħ

-0.14

ington

-0.14

 kelim

-0.14

anel

-0.14

ë°ĺ

-0.14

DMI

-0.14

ecko

-0.14

POSITIVE LOGITS

 camera

0.28

 scene

0.24

 perspective

0.24

 Perspective

0.24

 CAMERA

0.23

 pers

0.23

 Pers

0.22

 Camera

0.22

cam

0.22

camera

0.21

Activations Density 0.021%

code-related terminologies and functions

No Comments

No Known Activations