INDEX

Explanations

connections or relationships within a complex set of elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 particularly

-0.20

 besonders

-0.19

particularly

-0.19

anything

-0.17

especially

-0.17

 differently

-0.17

 especially

-0.17

pecially

-0.17

icularly

-0.17

 cualquier

-0.16

POSITIVE LOGITS

 plenty

0.43

 lots

0.40

an

0.36

 tons

0.35

 ample

0.32

 loads

0.32

 enough

0.29

lots

0.28

 tonnes

0.27

Activations Density 0.308%

connections or relationships within a complex set of elements

No Comments

No Known Activations