INDEX

Explanations

terms related to military training and qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Äįel

-0.16

cola

-0.15

CHASE

-0.15

èī¦

-0.15

dam

-0.15

urat

-0.14

 ÑĥÑģÐ»ÑĥÐ³

-0.14

.gc

-0.14

 coast

-0.14

(IService

-0.14

POSITIVE LOGITS

PT

0.21

 formation

0.20

 formations

0.20

 Leaders

0.19

bay

0.19

 Physical

0.17

 marching

0.17

 Formation

0.17

 rapp

0.17

 march

0.17

Activations Density 0.083%

terms related to military training and qualifications

No Comments

No Known Activations