INDEX

Explanations

elements related to physical structures or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

aims

-0.15

apses

-0.14

 Ð¿ÐµÑĢÐµÐ¹

-0.14

ãĥ¼ãĥľ

-0.14

haps

-0.14

 Bund

-0.14

InProgress

-0.14

izo

-0.13

strup

-0.13

Places

-0.13

POSITIVE LOGITS

sit

0.44

 sits

0.42

 lies

0.39

Sit

0.34

lie

0.34

Sit

0.33

 sitting

0.32

 situ

0.31

 overlook

0.31

sit

0.31

Activations Density 0.197%

elements related to physical structures or locations

No Comments

No Known Activations