INDEX

Explanations

references to tea and its various forms or related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

mente

-0.17

ry

-0.17

land

-0.15

teen

-0.15

tec

-0.15

lian

-0.14

ian

-0.14

te

-0.14

Dio

-0.14

entifier

-0.14

POSITIVE LOGITS

 Leaf

0.24

 leaf

0.24

Leaf

0.23

 Leaves

0.22

åı¶

0.21

leaf

0.21

 leaves

0.21

 towel

0.20

 bags

0.20

 ceremony

0.19

Activations Density 0.012%

references to tea and its various forms or related contexts

No Comments

No Known Activations