INDEX

Explanations

terms associated with reporting and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ingroup

-0.15

CString

-0.15

ibu

-0.14

UDA

-0.14

lemn

-0.13

illian

-0.13

 Transition

-0.13

isms

-0.13

 scare

-0.13

POSITIVE LOGITS

å²¡

0.14

ikk

0.14

ertino

0.14

adan

0.14

UAGE

0.14

ikh

0.14

Ø·Ø§ÙĤ

0.14

roduction

0.13

 UNIT

0.13

ENO

0.13

Activations Density 0.033%

terms associated with reporting and evaluation

No Comments

No Known Activations