INDEX

Explanations

words that start with the letter 'o'

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

-0.21

pas

-0.20

-0.19

rt

-0.18

pone

-0.18

POSITIVE LOGITS

lymp

0.29

'clock

0.25

vens

0.25

missions

0.23

curring

0.23

phthalm

0.23

scar

0.23

aths

0.22

regon

0.22

posite

0.21

Activations Density 0.011%

words that start with the letter 'o'

No Comments

No Known Activations