INDEX

Explanations

methods and functions related to testing and deserialization in code

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

azor

-0.14

icorn

-0.14

ancellable

-0.13

ãĥ§

-0.12

adden

-0.12

åŃĺäºİ

-0.12

_KP

-0.12

;↵↵

-0.12

çĶ

-0.11

 anytime

-0.11

POSITIVE LOGITS

CanBeConverted

0.28

 Should

0.28

Should

0.24

 Works

0.24

_should

0.23

 Does

0.22

 Wrong

0.22

Does

0.22

Throws

0.22

_returns

0.21

Activations Density 0.034%

methods and functions related to testing and deserialization in code

No Comments

No Known Activations