INDEX

Explanations

references to coding resources and documentation

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

__":↵

-0.17

/Dk

-0.17

__':↵

-0.16

_;↵

-0.15

::*;↵

-0.15

`}↵

-0.14

')+

-0.14

“.

-0.14

ContentLoaded

-0.14

kazy

-0.14

POSITIVE LOGITS

](

0.66

'](

0.37

"](

0.37

`](

0.35

](↵

0.31

#endif

0.30

][

0.30

"></

0.28

#else

0.28

></

0.28

Activations Density 0.011%

references to coding resources and documentation

No Comments

No Known Activations