INDEX

Explanations

concepts related to calibration and performance measurement in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

oya

-0.17

unbind

-0.14

toPromise

-0.14

hdl

-0.14

GLOBALS

-0.14

 promise

-0.13

 discrimin

-0.13

chez

-0.13

 Victor

-0.13

mk

-0.13

POSITIVE LOGITS

 systematic

0.30

 noise

0.27

 artifacts

0.27

 arte

0.27

 effects

0.25

noise

0.24

 artifact

0.23

 errors

0.23

 conf

0.22

effects

0.22

Activations Density 0.326%

concepts related to calibration and performance measurement in scientific contexts

No Comments

No Known Activations