INDEX

Explanations

references to size and dimension, specifically related to large objects or spaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

FFE

-0.15

ialis

-0.15

dit

-0.14

 dich

-0.14

kazy

-0.14

 sorts

-0.14

 Necklace

-0.14

ras

-0.14

 hass

-0.14

ian

-0.13

POSITIVE LOGITS

 Sized

0.16

foy

0.16

ÑĩÐ¸

0.15

stad

0.15

uja

0.15

uento

0.15

arendra

0.15

ometr

0.15

SIZE

0.15

olin

0.15

Activations Density 0.248%

references to size and dimension, specifically related to large objects or spaces

No Comments

No Known Activations