INDEX

Explanations

dates and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Barb

-0.16

ESA

-0.14

uem

-0.14

 proven

-0.14

sey

-0.14

meg

-0.14

ogenic

-0.14

ements

-0.13

ging

-0.13

POSITIVE LOGITS

PostalCodes

0.17

Ã¼nden

0.15

 licensors

0.15

esc

0.15

klÃ¤

0.15

ãĤĤãĤĬ

0.14

.generated

0.14

stroy

0.14

ëĮĢíķľ

0.14

è¨Ģãģ£ãģŁ

0.14

Activations Density 0.267%

dates and numerical data

No Comments

No Known Activations