INDEX

Explanations

names of individuals or characters

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

Ã©ric

-0.17

jeme

-0.16

 underst

-0.15

ierten

-0.15

ignum

-0.15

stav

-0.14

ouv

-0.14

ensibly

-0.14

igy

-0.14

noc

-0.14

POSITIVE LOGITS

rence

0.29

eed

0.25

dust

0.25

ein

0.25

akening

0.25

nee

0.25

yers

0.25

www

0.23

een

0.23

ww

0.23

Activations Density 0.025%

names of individuals or characters

No Comments

No Known Activations