INDEX

Explanations

words associated with happiness or expressions of gladness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

erli

-0.17

er

-0.15

frau

-0.15

etics

-0.15

ersed

-0.14

lectual

-0.14

ersh

-0.14

eri

-0.14

werk

-0.14

POSITIVE LOGITS

ys

0.24

stone

0.22

ness

0.20

win

0.19

tid

0.18

ewater

0.18

wyn

0.17

tid

0.17

dest

0.17

STONE

0.17

Activations Density 0.005%

words associated with happiness or expressions of gladness

No Comments

No Known Activations