INDEX

Explanations

terms related to optimization and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

rp

-0.16

ÅĻad

-0.16

.Management

-0.15

lesi

-0.15

itÃ©s

-0.15

ÏĢÎ®

-0.15

 Oliv

-0.14

æŃ

-0.14

perate

-0.14

POSITIVE LOGITS

imal

0.41

imum

0.40

imize

0.29

ics

0.26

IMAL

0.26

imized

0.25

IMUM

0.24

ima

0.24

ometry

0.23

imization

0.23

Activations Density 0.015%

terms related to optimization and measurements

No Comments

No Known Activations