INDEX

Explanations

terms related to photography and photographers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.20

oli

-0.16

uci

-0.15

ander

-0.15

combe

-0.14

anno

-0.14

ve

-0.13

page

-0.13

POSITIVE LOGITS

ically

0.22

/video

0.19

ical

0.18

ynthesis

0.17

isted

0.16

æ¢°

0.15

/music

0.15

/table

0.15

senal

0.14

linky

0.14

Activations Density 0.018%

terms related to photography and photographers

No Comments

No Known Activations