INDEX

Explanations

interactions and relationships between characters in a narrative

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

 Synopsis

-0.15

éĽĨä¸Ń

-0.14

REA

-0.14

 raining

-0.14

 Landing

-0.14

Ð³Ð°ÑĢ

-0.14

concert

-0.13

escal

-0.13

foc

-0.13

arih

-0.13

POSITIVE LOGITS

amb

0.34

sa

0.33

 walks

0.29

 walk

0.29

lim

0.28

 walking

0.27

walk

0.27

tr

0.27

tra

0.27

 walked

0.26

Activations Density 0.358%

interactions and relationships between characters in a narrative

No Comments

No Known Activations