INDEX

Explanations

documentation comments and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Mal

-0.15

olson

-0.15

@class

-0.14

uiten

-0.14

MAL

-0.14

otts

-0.14

ima

-0.14

ensor

-0.14

lear

-0.14

urb

-0.14

POSITIVE LOGITS

param

0.25

 param

0.19

 Exceptions

0.18

å¤ĩæ³¨

0.17

Exceptions

0.16

 exception

0.16

 EXCEPTION

0.15

 iParam

0.15

Exception

0.15

 Throws

0.15

Activations Density 0.012%

documentation comments and parameters

No Comments

No Known Activations