INDEX

Explanations

discussions related to personality types and social dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

inkle

-0.13

 Surround

-0.13

Ø¹ÙĨ

-0.13

 Ø¬ÙĦ

-0.13

çģ

-0.13

 Dank

-0.13

 Dwarf

-0.13

 unrelated

-0.12

 zusammen

-0.12

arget

-0.12

POSITIVE LOGITS

 oscill

0.39

amb

0.37

 split

0.35

 dich

0.32

 pend

0.31

 torn

0.30

 splits

0.30

 fluct

0.30

 neither

0.30

Osc

0.29

Activations Density 0.294%

discussions related to personality types and social dynamics

No Comments

No Known Activations