INDEX

Explanations

attributes and properties in code snippets, especially those related to data and configuration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

dil

-0.16

arde

-0.16

SizePolicy

-0.15

hear

-0.15

elenium

-0.14

_batches

-0.14

.batch

-0.14

etest

-0.14

acades

-0.14

rens

-0.14

POSITIVE LOGITS

 Balk

0.16

inker

0.16

FromFile

0.15

BERS

0.15

.tm

0.15

ondo

0.14

 Strand

0.14

UBL

0.14

.el

0.13

 Martial

0.13

Activations Density 0.002%

attributes and properties in code snippets, especially those related to data and configuration

No Comments

No Known Activations