INDEX

Explanations

numerical data and specific organism names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ARRANT

-0.15

ancellable

-0.15

orgia

-0.14

reira

-0.14

oure

-0.14

isko

-0.14

asto

-0.13

ilim

-0.13

Ã¼k

-0.13

 sert

-0.13

POSITIVE LOGITS

 Patri

0.40

 patriarch

0.29

Ec

0.27

 patri

0.26

Ec

0.24

ec

0.21

 Canterbury

0.20

 Millet

0.19

 Orth

0.19

 Metropolitan

0.19

Activations Density 0.060%

numerical data and specific organism names

No Comments

No Known Activations