INDEX

Explanations

terms related to photography and photographic processes

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

ean

-0.18

combe

-0.17

tim

-0.16

-fashioned

-0.16

leo

-0.16

-0.15

urance

-0.15

een

-0.14

POSITIVE LOGITS

/video

0.25

ically

0.23

 hÆ°á»Łng

0.21

journal

0.20

/videos

0.20

hoot

0.19

 volta

0.19

ynthesis

0.18

Taken

0.17

electric

0.16

Activations Density 0.036%

terms related to photography and photographic processes

No Comments

No Known Activations