INDEX

Explanations

mentions of military engagements and casualties

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

 armies

-0.18

 Armed

-0.18

 campaigns

-0.16

 armed

-0.15

 Fighter

-0.15

verity

-0.15

å¾ģ

-0.15

 military

-0.15

_war

-0.15

inventory

-0.15

POSITIVE LOGITS

 charge

0.26

 charging

0.22

 Charge

0.22

bay

0.20

Charge

0.20

 Charging

0.19

 advance

0.19

 charg

0.18

 charges

0.18

 gall

0.17

Activations Density 0.066%

mentions of military engagements and casualties

No Comments

No Known Activations