INDEX

Explanations

phrases that convey significance or purpose

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

STA

-0.15

bury

-0.15

eday

-0.14

urch

-0.14

åĭ¢

-0.14

uggy

-0.14

ipa

-0.14

icle

-0.14

adera

-0.14

WEBPACK

-0.14

POSITIVE LOGITS

fully

0.31

FUL

0.25

ful

0.25

lessly

0.22

fulness

0.21

lessness

0.20

nes

0.19

ings

0.19

iful

0.18

full

0.17

Activations Density 0.029%

phrases that convey significance or purpose

No Comments

No Known Activations