INDEX

Explanations

references to military commands and personnel

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

inear

-0.16

veau

-0.16

lob

-0.14

é³

-0.14

 Recruitment

-0.14

 recruitment

-0.13

 mercenaries

-0.13

_markup

-0.13

ruitment

-0.13

ourke

-0.13

POSITIVE LOGITS

 Fiscal

0.19

 Joint

0.18

 Petty

0.18

 Exercise

0.18

 Directorate

0.17

Col

0.17

 exercise

0.17

 fiscal

0.16

 subordinate

0.16

Activations Density 0.030%

references to military commands and personnel

No Comments

No Known Activations