INDEX

Explanations

references to military tactics and strategies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 turbulence

-0.16

 turbulent

-0.16

orman

-0.15

rosso

-0.15

Ã¡tek

-0.14

 skirm

-0.14

odÃŃ

-0.14

uml

-0.14

 seins

-0.14

POSITIVE LOGITS

 Superior

0.18

 deployments

0.17

 superior

0.17

 superiority

0.17

 capabilities

0.16

ponder

0.16

 losses

0.16

 effective

0.16

å¸«

0.15

 field

0.15

Activations Density 0.122%

references to military tactics and strategies

No Comments

No Known Activations