INDEX

Explanations

concepts related to change and transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

-0.17

ç´

-0.15

exels

-0.15

DisplayStyle

-0.15

okens

-0.14

ÑĸÑĤÐ¸

-0.14

ogn

-0.14

ibaba

-0.14

ossier

-0.14

-0.13

POSITIVE LOGITS

so

0.33

 likewise

0.30

 neither

0.29

Dit

0.28

 Likewise

0.28

Neither

0.27

 Neither

0.27

dit

0.22

Lik

0.22

itto

0.21

Activations Density 0.247%

concepts related to change and transformation

No Comments

No Known Activations