INDEX

Explanations

words associated with frivolity and serious consequences

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

ing

-0.17

ellation

-0.17

ingles

-0.17

tings

-0.16

ÐµÐ»Ñı

-0.16

ialias

-0.16

Ì§

-0.15

Carthy

-0.15

erged

-0.14

vider

-0.14

POSITIVE LOGITS

ous

0.91

ously

0.82

OUS

0.59

uous

0.42

ouser

0.37

oust

0.35

uos

0.33

ouse

0.33

osity

0.32

uously

0.31

Activations Density 0.079%

words associated with frivolity and serious consequences

No Comments

No Known Activations