INDEX

Explanations

terms related to optimization in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

oran

-0.18

 honour

-0.15

kes

-0.15

rp

-0.14

cle

-0.14

Ø©

-0.14

ings

-0.14

age

-0.14

ucer

-0.14

POSITIVE LOGITS

/max

0.22

imal

0.20

/opt

0.18

imum

0.18

IMUM

0.17

.cfg

0.17

/min

0.17

-eff

0.16

opis

0.16

ailer

0.15

Activations Density 0.018%

terms related to optimization in various contexts

No Comments

No Known Activations