INDEX

Explanations

mentions of prominent individuals and their affiliations or contributions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ffic

-0.14

ç¿Ķ

-0.14

å¸Ī

-0.14

 olarak

-0.14

_mgr

-0.14

Ø±Ø¨ÛĮ

-0.14

èĥ¸

-0.14

å®ĺ

-0.13

å¸«

-0.13

RAINT

-0.13

POSITIVE LOGITS

 another

0.29

 former

0.24

 fellow

0.22

another

0.18

one

0.18

our

0.17

åı¦ä¸Ģ

0.17

 erst

0.17

 longtime

0.17

 none

0.16

Activations Density 0.241%

mentions of prominent individuals and their affiliations or contributions in various contexts

No Comments

No Known Activations