INDEX

Explanations

comments and annotations related to code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ixels

-0.16

illance

-0.16

zte

-0.15

reur

-0.15

vous

-0.15

ä½łçļĦ

-0.14

ä½ł

-0.14

.Undef

-0.14

eus

-0.14

ixel

-0.13

POSITIVE LOGITS

XXX

0.26

 TODO

0.25

 Note

0.23

TODO

0.23

 NOTE

0.23

 todo

0.22

 HACK

0.22

 FIXME

0.22

NOTE

0.21

 hack

0.20

Activations Density 0.168%

comments and annotations related to code

No Comments

No Known Activations